diff --git a/doc/pub/NeuralNet/ipynb/NeuralNet.ipynb b/doc/pub/NeuralNet/ipynb/NeuralNet.ipynb
index 0561e394f..ecc1a8b39 100644
--- a/doc/pub/NeuralNet/ipynb/NeuralNet.ipynb
+++ b/doc/pub/NeuralNet/ipynb/NeuralNet.ipynb
@@ -597,10 +597,57 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAEWCAYAAACdaNcBAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvIxREBQAAIABJREFUeJzt3Xl4lNXZx/HvTXZIwhrCEjYVRDZZIi5tLSi2qLW21ipuVWtLbd2Xt63Lq7WLrXZRW62+1LUuoLZWUam7aV2qQgRF9rCHxYQEQhay3+8fM5aIgSQ4yTMz+X2uay7mmTkzzz2HyS8n59nM3RERkfjSJegCREQk8hTuIiJxSOEuIhKHFO4iInFI4S4iEocU7iIicUjhLh3CzK41s3ujbb1mts7Mpu3luTQze9bMyszsyfarstl1LzGzKR25TokviUEXIJ2Du98cg+s9FcgGert7fYRK+gwzexAodPfrP3nM3Ue31/qkc9DIXWTvhgAr2zPYRdqLwl0iysx+YmabzKzczFaY2bHhx39mZo80afcdM1tvZiVm9r9Np0fCbZ80s0fC77PYzEaY2TVmVmRmG83sK03ea4CZzTWzUjMrMLPvN3luz/We02S91+3jc9wE3ACcbmYVZnZBM+811MzczBLDy3lm9gszeytc90tm1qdJ+y+a2dtmtiP8Gc4zs5nAWcCPw+t5Nty2aX+kmNntZrY5fLvdzFLCz00xs0IzuyrcN1vM7Pz9/f+T+KFwl4gxs4OBi4HD3D0D+Cqwrpl2o4A/Ewq1/kB3YOAezU4CHgZ6AguBFwl9XwcCPwf+r0nb2UAhMIDQVMrNn/xSaWa9dwPnhNv2BnKa+yzufiNwM/C4u6e7+30tdkDImcD5QF8gGbg6vO7BwD+BPwFZwHhgkbvPAh4Fbg2v56Rm3vM64Ijwaw4FJgPXN3m+H7v78ALgLjPr2cp6JU4p3CWSGoAUYJSZJbn7Ondf3Uy7U4Fn3f1Nd68lNELe8yRHb7j7i+EpkScJBeJv3L0OmAMMNbMeZjYI+CLwE3evdvdFwL2EAry59T7n7v929xrgf4HGz/+xP+UBd1/p7ruAJwgFMoR+kb3i7rPdvc7dS8K1tsZZwM/dvcjdi4Gb+PTnqws/X+fu84AK4ODIfByJVQp3iRh3LwAuB34GFJnZHDMb0EzTAcDGJq+rAkr2aPNxk/u7gG3u3tBkGSA9/F6l7l7epP16PvuXQHPrrWxmvZ/X1ib3q8I1AgwCmvtF1xoDCH2mT6wPP/aJkj22CzRdr3RSCneJKHd/zN2/SGhjpAO3NNNsC02mQ8wsjdAUyf7YDPQys4wmjw0GNu1lvYOarLdrG9dbCXRtstyvDa/dCBy4l+daOjXrZkL9+YnB4cdE9krhLhFjZgeb2THhjX3VhEbYDc00/RtwkpkdZWbJhKYZbH/W6e4bgbeBX5tZqpmNIzTv/Ohe1vu18IbNZEJz9235GVgEHG1mg82sO3BNG177KDDNzE4zs0Qz621mn0zZfAwcsI/XzgauN7Os8AbaG4BH9tFeROEuEZUC/AbYRmh6oi9w7Z6N3H0JcAmhufMtQDlQBNTs53rPAIYSGs3+A7jR3V/ey3ovAh4Lr3c7oQ2xrRJ+z8eBD4F84Lk2vHYDcAJwFVBK6BfFoeGn7yO0nWKHmT3dzMt/CSwIr3cx8H74MZG9Ml2sQ4JmZunADmC4u68Nuh6ReKCRuwTCzE4ys65m1g34HaER6bpgqxKJHwp3CcrJhKZRNgPDgRmuPyNFIkbTMiIicUgjdxGROBTYWSH79OnjQ4cODWr1/1VZWUm3bt2CLiMqqC9C1A+7qS92i5a+yM/P3+buWS21Cyzchw4dyoIFC4Ja/X/l5eUxZcqUoMuICuqLEPXDbuqL3aKlL8xsfcutNC0jIhKXFO4iInFI4S4iEocU7iIicUjhLiIShxTuIiJxSOEuIhKHFO4iInFI4S4iEocU7iIicUjhLiIShxTuIiJxSOEuIhKHWgx3M7vfzIrM7KO9PG9m9kczKzCzD81sYuTLFBGRtmjNyP1BYPo+nj+e0GXShgMzgbs/f1kiIvJ5tBju7v5voHQfTU4G/uoh7wA9zKx/pAoUEZG2i8TFOgYCG5ssF4Yf27JnQzObSWh0T3Z2Nnl5eRFY/edTUVERFXVEA/VFiPphN/XFbrHWF5EId2vmsWavuu3us4BZALm5uR4NVzWJlqurRAP1RYj6YTf1xW5t7Qt3p7ymnp276iivDv27s7qeipo6KqrrKa+pp6K6nsqaeipqGqiqraeytoFdtfVU1jRQXddAVW3o8XvOnsRRB/VpU72RCPdCYFCT5RxgcwTeV0QkatQ1Opt27GJbeQ3F5TWUVtZSUllLSUUNpVW17Kiqo7Sylh1VtZSFg7yhsdlx7n8ldDG6JSeQnpJIt5REuqYk0i05gQE9kkhLTiQtqQtdkxPJykhpc72RCPe5wMVmNgc4HChz989MyYiIRKvKmno27djFpu272Fy2i61l1Wwpq+bjnZ/caijbVQcvvfaZ16YmdaF3txR6dE2iV7dkBvXqSo+0JLo3uWWmJZKZmkR6aiIZqUlkpCaSnpJISmIXzJqb/Pj8Wgx3M5sNTAH6mFkhcCOQBODu9wDzgBOAAqAKOL9dKhUR2U/uTnFFDWuLK1m7rZL1pVVsKK1iY/i2varuU+27GPTNSCW7eyrD+nTjiAN6U7FtM5PHjiQrI4U+6Sn0Tk+md7cU0pITAvpU+9ZiuLv7GS0878BFEatIRGQ/uTtbyqpZsbWcFR+XU1BUwaqiCtYUVVBeU//fdoldjJyeaQzq1ZUxY/uT0zONgT3SyOmZxoAeaWSlp5CY8OmdCfPytjFl8uCO/kj7LRLTMiIiHa6h0VlTXMFHm8v4aNNOPtpUxrItO9lZvTvE+2akMDw7nVMmDuSArHSG9unGAX260b976mfCO94o3EUkJpRW1pK/fjv567fzwcYdLN5URkV4NJ6a1IVD+mfytUMHcEi/DEb2z2REdgbd05ICrjo4CncRiUrF5TX8Z00J/1ldwvx1pRQUVQCQlGAc0j+Tb04YyKGDejAupzsH9OkW9yPxtlK4i0hUqK5r4L21pfx7ZTH/XlXMyo9DYZ6Rkkju0J58c8JADhvai3E53UlNis6NmNFE4S4igSnaWc2ry4t4ZenHvLV6G9V1jSQndmHy0F58c0IORx3Ym9EDMjUq3w8KdxHpUJt27OKfi7fw/OItLNywA4CcnmnMOGwwXz44iyOG9Y7a3QtjicJdRNpdaWUtz36wmWcWbeL9cKCPHpDJVceN4LjR2RycndFuB/N0Vgp3EWkXdQ2NvLqsiL/lbyRvRTH1jc7Ifhn8z1cP5sSx/Rnap1vQJcY1hbuIRNSGkirmzN/Ak/mFFJfXkJ2ZwgVfHMY3Jw5kZL/MoMvrNBTuIvK5uTtvFZTw4NtreXV5EQYcM7IvZ0wezJdHZGmDaAAU7iKy32rrG3l64Sb+8sYaVhVV0LtbMpdMPYgzDh9M/+5pQZfXqSncRaTNKmrqmf3uBu57cy1bd1Yzqn8mv//2oXzt0P6kJGpPl2igcBeRVqusqeev/1nPrH+vZntVHUce0JtbTx3Hl4b30d4uUUbhLiItqq5r4JF31nN33mpKKmv58ogsLps2nImDewZdmuyFwl1E9qrRnafeL+T3L61k045dfPGgPlxx3AgmDVGoRzuFu4g06501Jfzs7Wo2lH/AmIGZ/PbUcW2+jqcER+EuIp+ypWwXv3p+Gc99uIXeqcYdM8Zz0rgBdOmiOfVYonAXESB0ROl9b67ljldW0ejOZccOZ1SXTXx1/MCgS5P9oHAXET4s3MFP/r6YZVt2Mu2QbG48aRSDenUlL29z0KXJflK4i3Ri1XUN/O7FFdz/1lqyMlK45+xJTB/TL+iyJAIU7iKd1MIN27nqyQ9YU1zJWYcP5ifHjyQztfNeli7eKNxFOpna+kbueHUld+etpl9mKo9+73C+oL1g4o7CXaQTWbetkkvnLOTDwjK+PSmH/z1plEbrcUrhLtJJPLNoE9f94yO6GNxz9kSmj+kfdEnSjhTuInGuuq6BG59ZwuMLNpI7pCe3zxhPTs+uQZcl7UzhLhLHNpZW8cNH8/lo004umnogV0wboXOrdxIKd5E49a+VxVw2ZyENjc6938ll2qjsoEuSDqRwF4kz7s69b6zl5n8u4+DsDO45e5KuV9oJtervMzObbmYrzKzAzH7azPODzex1M1toZh+a2QmRL1VEWlJT38CP//Yhv5q3jOmj+/HUj45SsHdSLY7czSwBuAs4DigE5pvZXHdf2qTZ9cAT7n63mY0C5gFD26FeEdmL0spafvDwAuav286lxxzE5dNG6GRfnVhrpmUmAwXuvgbAzOYAJwNNw92BTy5r3h3QCSlEOtD6kkrOvf89NpdVc8eM8Zysk311eubu+25gdiow3d2/F14+Bzjc3S9u0qY/8BLQE+gGTHP3/GbeayYwEyA7O3vSnDlzIvU59ltFRQXp6elBlxEV1BchsdYPa8oauC2/mkaHyyemMrxn5K5hGmt90Z6ipS+mTp2a7+65LbVrzci9ub/r9vyNcAbwoLv/3syOBB42szHu3vipF7nPAmYB5Obm+pQpU1qx+vaVl5dHNNQRDdQXIbHUD68t/5jfvrqQPhlpPHj+ZA7Mimz4xFJftLdY64vWhHshMKjJcg6fnXa5AJgO4O7/MbNUoA9QFIkiReSznlm0iSuf+IBD+mdw/3mH0TcjNeiSJIq0Zm+Z+cBwMxtmZsnADGDuHm02AMcCmNkhQCpQHMlCRWS3h99Zz+WPLyJ3SE9mf/8IBbt8Rosjd3evN7OLgReBBOB+d19iZj8HFrj7XOAq4C9mdgWhKZvzvKXJfBHZL3fnreaWF5Zz7Mi+3HXWRFKTIjfHLvGjVQcxufs8Qrs3Nn3shib3lwJfiGxpIrKn219Zye2vrOLrhw7g96cdSpJOJSB7oSNURWKAu3Pbyyv542sFnDoph1u+NY4E7cMu+6BwF4ly7s7vXlrBXa+v5vTcQfz6lLE6OElapHAXiXK/f2kld72+mjMmD+ZX3xijYJdW0YSdSBS787VV3Pl6AWdMHqRglzZRuItEqXvfWMPvXlrJKRMG8qtvaCpG2kbhLhKFHn13Pb98fhknju3PraeOU7BLmyncRaLMcx9u5vqnP+LYkX257fTxunKS7Bd9a0SiyL9XFnPF44s4bGgv7jprIsmJ+hGV/aNvjkiUWLhhOz94OJ+D+mZw77m5OvJUPheFu0gUKCiq4PwH59M3M4WHvnsYmalJQZckMU7hLhKwovJqznvgPRK7GH/97mSdBEwiQgcxiQSosqaeCx5cQElFLY//4AiG9Nb1TiUyNHIXCUh9QyMXPfY+SzaXcddZExiX0yPokiSOaOQuEgB354a5S8hbUczN3xzLMSOzgy5J4oxG7iIBuO/NtTz27gYu/PKBnHn44KDLkTikcBfpYK8s/ZhfzVvG9NH9+PFXDw66HIlTCneRDrRkcxmXzlnI2IHdue308TqtgLQbhbtIBykur+F7Dy2ge1oS934nl7RkHaQk7UcbVEU6QE19Axc+ks+OqjqevPBI+mZqX3ZpXwp3kXbm7lz/j4/IX7+du86cyJiB3YMuSToBTcuItLMH3lrHk/mFXHrscE4c1z/ocqSTULiLtKM3V23jl88v5aujs7n82OFBlyOdiMJdpJ1sLK3i4tnvc1DfdP5wmvaMkY6lcBdpB7tqG/jBw/k0NDqzzsmlW4o2b0nH0jdOJMLcnWue+pBlW3dy37m5DO2jk4FJx9PIXSTCHnhrHU8v2syV00bonDESGIW7SATNX1fKzfOWcdyobC6aelDQ5Ugn1qpwN7PpZrbCzArM7Kd7aXOamS01syVm9lhkyxSJfkXl1Vz06Pvk9Ezj96cdqg2oEqgW59zNLAG4CzgOKATmm9lcd1/apM1w4BrgC+6+3cz6tlfBItGovqGRSx5byM7qOh767mRdJk8C15qR+2SgwN3XuHstMAc4eY823wfucvftAO5eFNkyRaLbrS+u4N21pfz6lLEc0j8z6HJEWrW3zEBgY5PlQuDwPdqMADCzt4AE4Gfu/sKeb2RmM4GZANnZ2eTl5e1HyZFVUVERFXVEA/VFSFv7If/jemYtrOGYwYn0LCsgL6+g/YrrYPpO7BZrfdGacG9u4tCbeZ/hwBQgB3jDzMa4+45Pvch9FjALIDc316dMmdLWeiMuLy+PaKgjGqgvQtrSDxtKqrgk7w0OzenO3TOPJCUxvs70qO/EbrHWF62ZlikEBjVZzgE2N9PmGXevc/e1wApCYS8St6rrGvjho/l0MePOMyfGXbBLbGtNuM8HhpvZMDNLBmYAc/do8zQwFcDM+hCaplkTyUJFos1Nzy5lyead/OG0QxnUq2vQ5Yh8Sovh7u71wMXAi8Ay4Al3X2JmPzezr4ebvQiUmNlS4HXgf9y9pL2KFgnaM4s2Mfu90DVQjz1EBypJ9GnV6QfcfR4wb4/Hbmhy34ErwzeRuFZQVME1Ty3msKE9uforI4IuR6RZOkJVpA121TZw0aPvk5qUwB/PmEBign6EJDrpxGEibXDTs0tY8XE5D55/GP27pwVdjsheadgh0kpPL9zEnPkb+dGUA5lysA7CluimcBdphdXFFVz7j9A8+5XHaZ5dop/CXaQF1XWhefaUxC6aZ5eYoTl3kRb84rmlLN9azgPnaZ5dYoeGICL78NyHm3n03Q384OgDmDpS8+wSOxTuInuxvqSSa/6+mAmDe3D1Vw8OuhyRNlG4izSjtr6RS2YvxAz+OGMCSZpnlxijOXeRZtzywnI+LCzjnrMn6rwxEpMU7iJ7WFhUz33vr+U7Rw5h+pj+QZcjsl/0t6ZIE1vKdnHv4hpG9c/k2hMOCbockf2mcBcJq29o5NLZC6lvhDvPnEBqks7PLrFL4S4Sdserq5i/bjvnjk7hgKz0oMsR+VwU7iLAm6u2cefrBXx7Ug5HDdCmKIl9Cnfp9IrLa7j88UUcmJXOTSePDrockYjQEEU6tcZG58onFlFeXccj35tM12T9SEh80MhdOrW7/7WaN1Zt48aTRjOyX2bQ5YhEjMJdOq3560r5w8srOenQAZwxeVDQ5YhElMJdOqXSyloueWwhg3qmcfM3x2BmQZckElGaYJROp7HR+Z8nP6C0spanfnQUGalJQZckEnEauUunc++ba3h1eRHXnXgIYwZ2D7ockXahcJdOJX99Kbe8sIITxvbjO0cOCbockXajcJdOY3t4nn1gjzR+861xmmeXuKY5d+kUGhudq578gG0Vtfz9h0eRqXl2iXMauUun8H//XsNry4u4/muHMDZH8+wS/xTuEvfeXVPC715awYnj+nPOEZpnl86hVeFuZtPNbIWZFZjZT/fR7lQzczPLjVyJIvuvuLyGS2YvZEivrtyieXbpRFoMdzNLAO4CjgdGAWeY2ahm2mUAlwLvRrpIkf3R0OhcNmchO6vr+PPZE0lP0SYm6TxaM3KfDBS4+xp3rwXmACc30+4XwK1AdQTrE9lvt7+ykrdXl/CLk8fovDHS6bRmKDMQ2NhkuRA4vGkDM5sADHL358zs6r29kZnNBGYCZGdnk5eX1+aCI62ioiIq6ogG8dQXi4rq+dP7NXxpYCJZFavJy1vd6tfGUz98XuqL3WKtL1oT7s1NUvp/nzTrAtwGnNfSG7n7LGAWQG5urk+ZMqVVRbanvLw8oqGOaBAvfbGhpIpL//QGowdk8pcLj2rz5fLipR8iQX2xW6z1RWumZQqBpqfMywE2N1nOAMYAeWa2DjgCmKuNqhKE6roGLnwkHzPjnrMn6Tqo0mm1JtznA8PNbJiZJQMzgLmfPOnuZe7ex92HuvtQ4B3g6+6+oF0qFtkLd+f6pz9i2dad3H76eAb16hp0SSKBaTHc3b0euBh4EVgGPOHuS8zs52b29fYuUKS1Hnl3A3/LL+SSY4YzdWTfoMsRCVSr9g1z93nAvD0eu2Evbad8/rJE2mb+ulJumruEqQdncfmxw4MuRyRwOkJVYt7Wsmp++Mj75PRM4/YZE+jSRQcqieioDolpNfUN/PDRfKpq63ns+4fTPU0nBBMBhbvEMHfnhqeXsHDDDv581kRGZGcEXZJI1NC0jMSsh95ex+MLNnLJMQdxwtj+QZcjElUU7hKT3ly1jV88v4zjRmVzxbQRQZcjEnUU7hJz1m2r5KLH3uegrHRuO328NqCKNEPhLjGlbFcdFzw0ny4G956bqzM9iuyFfjIkZtQ1NPKjR/PZUFrFwxccriNQRfZB4S4xwd254ZklvFVQwu++fShHHNA76JJEopqmZSQm3PfmWma/t4EfTTmQUyflBF2OSNRTuEvUe+GjLfxq3jKOH9OPq79ycNDliMQEhbtEtfz1pVw2ZxETBvXQnjEibaBwl6i1uriCCx5awIAeadx77mE6N7tIGyjcJSoVl9dw3gPvkWDGg+cfRq9uyUGXJBJTtLeMRJ2d1XWc98B7FJfXMGfmkQzp3S3okkRijkbuElWq6xr4/kMLWLG1nLvPnsT4QT2CLkkkJmnkLlGjvqGRS2cv5N21pdwxYzxTD9bVlET2l0buEhUaG51rnlrMS0s/5mcnjeLk8QODLkkkpincJXDuzo1zl/BkfiGXHjuc874wLOiSRGKewl0C5e7cPG8ZD7+znplHH8AV03T9U5FIULhLoG57eSV/eWMt5x45hGuOH4mZDlISiQRtUJVAuDu3v7KKP75WwGm5Odx40mgFu0gEKdylw7k7f3h5JX96rYBvT8rh16eM02kFRCJM4S4dyt357Ysr+HPeak7PHcSvTxmrYBdpBwp36TCfbDz9yxtrOWPyYH71jTEKdpF2onCXDtHQ6Fz71GIeX7CR7xw5hJ+dNFrBLtKOFO7S7mrrG7ni8UU8v3gLlxxzEFceN0IbT0XaWat2hTSz6Wa2wswKzOynzTx/pZktNbMPzexVMxsS+VIlFlXW1PO9vy7g+cVbuPaEkVz1lYMV7CIdoMVwN7ME4C7geGAUcIaZjdqj2UIg193HAX8Dbo10oRJ7isqrOX3Wf3irYBu3fGssM48+MOiSRDqN1ozcJwMF7r7G3WuBOcDJTRu4++vuXhVefAfQRS47uYKiCk7589usLqrk3u/kcvphg4MuSaRTMXffdwOzU4Hp7v698PI5wOHufvFe2t8JbHX3Xzbz3ExgJkB2dvakOXPmfM7yP7+KigrS09ODLiMqRKovlpU0cOeiahIMrpiUyrDusXUFJX0ndlNf7BYtfTF16tR8d89tqV1rNqg2N0Ha7G8EMzsbyAW+3Nzz7j4LmAWQm5vrU6ZMacXq21deXh7RUEc0iERfzH5vA79/6SOG9O7GA+dNZnDvrpEprgPpO7Gb+mK3WOuL1oR7ITCoyXIOsHnPRmY2DbgO+LK710SmPIkV9Q2N3DxvOfe/tZajR2Rx55kTyExNCroskU6rNeE+HxhuZsOATcAM4MymDcxsAvB/hKZviiJepUS1kooaLpuziDcLtnH+F4Zy3QmHkJigc9KJBKnFcHf3ejO7GHgRSADud/clZvZzYIG7zwV+C6QDT4Z3c9vg7l9vx7olSnywcQc/fCSfbZW13PqtcZx22KCWXyQi7a5VBzG5+zxg3h6P3dDk/rQI1yVRzt157L0N3DR3KVkZKfz9wqMYm9M96LJEJExHqEqble2q49qnFvP84i0cPSKLO04fT89uyUGXJSJNKNylTd7fsJ1LZy9kS1k1P5k+kh8cfYDOESMShRTu0ip1DY3c+VoBd75eQP/uqTx54ZFMHNwz6LJEZC8U7tKiVR+Xc+UTH7B4UxnfGD+Am04eQ/c07eYoEs0U7rJXdQ2N3PvGWm57ZSXpKYncfdZEjh/bP+iyRKQVFO7SrA8Ld/CTvy9m2ZadfHV0Nr/8xliyMlKCLktEWknhLp+ys7qO219exYNvryUrI4V7zp7E9DH9gi5LRNpI4S4ANDY6bxTWcfXv8iiprOWswwfz4+kjdQoBkRilcBfy12/nl88vZeGGWiYO7sED503WAUkiMU7h3omtKa7g1hdW8MKSrWRlpPD9sclcc8ZR2m9dJA4o3DuhTTt2cedrBTyxYCOpiV248rgRfO9Lw3jv7TcV7CJxQuHeiWwp28WfX1/NnPkbMIyzDh/MJccM114wInFI4d4JrC6uYNa/1vDUwkLc4bTDBnHR1IMY2CMt6NJEpJ0o3OOUu7Ng/Xbue2MtLy7dSnJCF2YcNpiZRx/AoF6xd3UkEWkbhXucqa5r4NkPNvPg2+tYsnkn3dOSuHjqQZx71FD6pGv6RaSzULjHiVUflzP7vY08tbCQHVV1jMhO5+ZvjuUbEwbQNVn/zSKdjX7qY1hZVR3PLd7MU+9vIn/9dpISjK+M7sdZkwdz5IG9CV8VS0Q6IYV7jKmqref15cU8+8FmXlteRG1DI8P7pnPN8SM5dVIOvTX1IiIo3GPCzuo6/rWimBc+2spry4vYVddAn/QUzj5iCKdMHMjoAZkapYvIpyjco5C7s66kin+tKOKVZUW8s6aE+kanT3oy35o0kBPHDmDysF4k6IAjEdkLhXuU2F5ZyztrSnhr9Tb+tbKYjaW7ADgwqxsXfGkYXxmVzfhBPRXoItIqCveAFO2sZsH67SxYt5131pSwbOtO3KFrcgJHHdibmV86gKNHZDGkd7egSxWRGKRw7wDVdQ0s2byTDzbuYFH4tqG0CoDUpC5MGNSTK6eN4KiDejMupwdJCV0CrlhEYp3CPcK2VdSwfEs5y7fuZOnmnXy0uYzVxZU0NDoA/buncmhOD845Ygi5Q3syekB3khMV5iISWQr3/dDQ6GzesYu12ypZU1xBQXEFqz6uYHVxBdsqav/bLisjhbEDuzN9dD9GD+zO+EE9yM5MDbByEeksFO7NcHd2VNVRuH0Xm3ZUUbh9FxtLq9gQvm0s3UVtQ+N/22emJjI8O4NjR2Yzol8GI/tlcHC/DB3uLyKB6VTh7u5U1NRTXF7DtopatlXU8Na6Ot7553KKyqvZWha6bSmrZlddw6dem56SyOBeXRneN4Npo7I5oE83hvbuxrCedmTGAAAGF0lEQVSsbmSlp2g/cxGJKjEZ7u5OVW0D5dX17KyuY+euOsqa3HZU1bGjqpbtVXVsr6qlpKKW0spaSqtqqa1v/Mz7Ja1aQ1Z6Cv26p3JI/0yOGdmXft1TyenZlZyeaQzskUaPrkkKcBGJGa0KdzObDtwBJAD3uvtv9ng+BfgrMAkoAU5393X7es+d1XU8+8FmdtU1UF3XwK7aBqpqQ/cra+upqgn/W9tARU09lTX1VNY0UF5dR0VNPeHtk3uVmZpIr27J9OiaTL/uqYwekEmv9GR6d0smKyOFPumhW8HifE6cNkVXIBKRuNJiuJtZAnAXcBxQCMw3s7nuvrRJswuA7e5+kJnNAG4BTt/X+64vqeKS2Qs/83hqUhe6JifSNTmBbsmJpCUnkJGaSHZGKt1SEslIDd3SUxLJTEsiIzWRzNQkMtOS6J6WRI/wY4mt3J3w4xWmYBeRuNOakftkoMDd1wCY2RzgZKBpuJ8M/Cx8/2/AnWZm7r7X8fVBWek8c+XRpCQmkJqUQNfkBNKSEhS0IiIR0JpwHwhsbLJcCBy+tzbuXm9mZUBvYFvTRmY2E5gJkJ2dTeHS/P0sO3IqKirIy8sLuoyooL4IUT/spr7YLdb6ojXh3txQes8ReWva4O6zgFkAubm5PmXKlFasvn3l5eURDXVEA/VFiPphN/XFbrHWF62ZmC4EBjVZzgE2762NmSUC3YHSSBQoIiJt15pwnw8MN7NhZpYMzADm7tFmLnBu+P6pwGv7mm8XEZH21eK0THgO/WLgRUK7Qt7v7kvM7OfAAnefC9wHPGxmBYRG7DPas2gREdm3Vu3n7u7zgHl7PHZDk/vVwLcjW5qIiOwvnY5QRCQOKdxFROKQwl1EJA4p3EVE4pDCXUQkDincRUTikMJdRCQOKdxFROKQwl1EJA4p3EVE4pDCXUQkDincRUTikAV1Zl4zKwbWB7LyT+vDHleM6sTUFyHqh93UF7tFS18McfeslhoFFu7RwswWuHtu0HVEA/VFiPphN/XFbrHWF5qWERGJQwp3EZE4pHAPX7BbAPXFJ9QPu6kvdoupvuj0c+4iIvFII3cRkTikcBcRiUMK9zAzu9rM3Mz6BF1LUMzst2a23Mw+NLN/mFmPoGvqaGY23cxWmFmBmf006HqCYmaDzOx1M1tmZkvM7LKgawqamSWY2UIzey7oWlpD4U7oiwwcB2wIupaAvQyMcfdxwErgmoDr6VBmlgDcBRwPjALOMLNRwVYVmHrgKnc/BDgCuKgT98UnLgOWBV1EayncQ24Dfgx06q3L7v6Su9eHF98BcoKsJwCTgQJ3X+PutcAc4OSAawqEu29x9/fD98sJhdrAYKsKjpnlACcC9wZdS2t1+nA3s68Dm9z9g6BriTLfBf4ZdBEdbCCwsclyIZ040D5hZkOBCcC7wVYSqNsJDQAbgy6ktRKDLqAjmNkrQL9mnroOuBb4SsdWFJx99YW7PxNucx2hP8sf7cjaooA181in/mvOzNKBvwOXu/vOoOsJgpl9DShy93wzmxJ0Pa3VKcLd3ac197iZjQWGAR+YGYSmId43s8nuvrUDS+wwe+uLT5jZucDXgGO98x0EUQgMarKcA2wOqJbAmVkSoWB/1N2fCrqeAH0B+LqZnQCkAplm9oi7nx1wXfukg5iaMLN1QK67R8OZ3zqcmU0H/gB82d2Lg66no5lZIqENyccCm4D5wJnuviTQwgJgodHOQ0Cpu18edD3RIjxyv9rdvxZ0LS3p9HPu8il3AhnAy2a2yMzuCbqgjhTemHwx8CKhDYhPdMZgD/sCcA5wTPi7sCg8cpUYoZG7iEgc0shdRCQOKdxFROKQwl1EJA4p3EVE4pDCXUQkDincRUTikMJdRCQOKdxFwszswiYH7Kw1s9eDrklkf+kgJpE9hM+p8hpwq7s/G3Q9IvtDI3eRz7oDeE3BLrGsU5wVUqS1zOw8YAihc8yIxCxNy4iEmdkkQmdC/JK7bw+6HpHPQ9MyIrtdDPQCXg9vVI2ZS6qJ7EkjdxGROKSRu4hIHFK4i4jEIYW7iEgcUriLiMQhhbuISBxSuIuIxCGFu4hIHPp/rfvuMPOvIFYAAAAASUVORK5CYII=\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "%matplotlib inline\n",
     "\n",
@@ -1520,10 +1567,30 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "inputs = (n_inputs, pixel_width, pixel_height) = (1797, 8, 8)\n",
+      "labels = (n_inputs) = (1797,)\n",
+      "X = (n_inputs, n_features) = (1797, 64)\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAArwAAACiCAYAAACj+R6BAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvIxREBQAAC3JJREFUeJzt3V+I5edZB/DnbTdQ6589BkXUJrvaohAvMjeiYmXPgiAIMgMhIlizs6LgVXdD9UaQmZV6IV5kVrzQq8w2ghUtzIAGQXRntEbRQmbBm4CUaWNpsZWcaaIiWl8vziwMYZOdPL9z5px95vOBgdlwnt/z/uY85z3f85tzJq33HgAAUNX7Fr0AAACYJ4EXAIDSBF4AAEoTeAEAKE3gBQCgNIEXAIDSBN4HaK3ttdZ+6axrefSYFU7DnHBaZoXTMCfvXenA21o7bK395KLX8U7a1Cdba19qrR0dD+EPLXpd59EjMCu/31p768TXf7fW3lz0us4bc8JpPQKz8nOttdeOn3v+rbV2p7X2bYte13ljTs5O6cD7CHg2In4xIn4iIh6PiL+PiJcWuiKWUu/9V3rv33L/KyL+KCL+ZNHrYrmYE96Dv4uIH++9X4yI74+ICxHxycUuiSVUZk7OZeBtrX17a+3PWmtfba29cfz9h952sw+31v7x+FXNbmvt8RP1P9pae6W1Nmmt3WutjZNL+b6I+Gzv/fO9929ExB9GxFPJYzEHSzQrJ9f0zRHxTETcGXosZsOccFrLMiu999d771878Z++EREfyRyL2TMns3cuA29Mz/vFiLgUEU9GxH9FxO+97TbPxfTq6/dExP9GxO9GRLTWvjci/jymr3Aej4hfjYjPtNa+8+1NWmtPHg/bk++wjk9HxEdaaz/QWnssIq5FxF8MPDdma1lm5aRnIuKrEfE3mRNiLswJp7U0s9Ja+2hr7Sgi3ozpvGwNOzVmyJzM2LkMvL33f++9f6b3/p+99zcj4rci4srbbvZS7/2fe+//ERG/ERE/21p7f0R8LCJe7r2/3Hv/v977X0bE5yLipx/Q54u991Hv/YvvsJQvR8TfRsRrMR3mZyPi+ZmcJDOxRLNy0rWI+FTvvQ86OWbGnHBayzQrvffPHv+q+kMR8TsRcTiTk2QwczJ75zLwttY+2Fr7g9baF1prX4/pFZDR8aDc9/qJ778QEY9FxHfE9NXWs8eviCattUlEfDQivjuxlI2I+OGIeCIiPhARtyLir1trH0wcizlYolm5v54nYrrpfSp7DGbPnHBayzYrERG99y/F9LeLnx5yHGbHnMzehUUvYEE+ERE/GBE/0nv/SmttJSJejYh24jZPnPj+yYj4n4j4WkwH7KXe+y/PYB1PR8Qf997/9fjf2621rZi+j/dzMzg+wy3LrNz3XES80nv//AyPyXDmhNNatlm570JEfHgOxyXHnMzYebjC+1hr7QMnvi5ExLfG9C0Ek+M3eW88oO5jrbWnjq+2/mZE/OmJD5b9TGvtp1pr7z8+5vgBbyY/jX+K6auw72qtva+19gsxfYX2L6kzZahlnpX7nouI7QH1DGdOOK2lnZXW2s8fv3+ztdYuxfRX5n+VPlOGMCdn4DwE3pdjOjT3vzZj+obrb4rpK6F/iAd/UOylmD5hfCWmbzf4eMT0E4sRsRoRvx7TD4S8HhG/Fg/4WR4PyVvtnd8M/tsRcS8iDiJiEtP37z7Te5+899NkBpZ5VqK19mMxfQ+VPzO1WOaE01rmWXkqIl6JiLdi+qenXouIeVwR5OHMyRloPs8AAEBl5+EKLwAA55jACwBAaQIvAAClCbwAAJQ2r7/De+afhNve3k7VbW5upnuORqNU3dZW/v/KNx6P07UDtIffJOXM52Rvby9Vl52viIidnZ1U3dHRUbrn3bt3U3UD52tecxKxgFnZ3d1N1d24cWPGK3m47FxHRFy+fHlm63gPlmpPOTw8TDfM7udD9pTs3nDx4sV0z4ODg1TdwPlauj1lMsn/EaVFzEp2vdn7O2J59xRXeAEAKE3gBQCgNIEXAIDSBF4AAEoTeAEAKE3gBQCgNIEXAIDSBF4AAEoTeAEAKE3gBQCgNIEXAIDSBF4AAEoTeAEAKO3Cohdw0t7eXrr2+vXrqbrV1dV0z9FolKpbW1tL95xMJulaIm7evJmqG/JzX19fT9Xdvn073TM7m9UcHh6ma4c8Ts/azs5Oujb7mKhkET+DO3fupGvv3r2bqhuyp3jumRryc8g+TofsRdme29vb6Z6bm5vp2nlyhRcAgNIEXgAAShN4AQAoTeAFAKA0gRcAgNIEXgAAShN4AQAoTeAFAKA0gRcAgNIEXgAAShN4AQAoTeAFAKA0gRcAgNIEXgAASmu993kcN3XQmzdvphseHh6m6nZ2dtI9x+Nxqm40GqV7DlnvAG1Ox53L8L2b7JwMuc/29/dTddeuXUv3nEwm6doB5jUnEQuYla2trVTdyspKuufVq1dTdVeuXEn33NvbS9cOUGZPWYTsc+XBwUG6Z7E5iTgns5LNKUP2sezeOdBDZ8UVXgAAShN4AQAoTeAFAKA0gRcAgNIEXgAAShN4AQAoTeAFAKA0gRcAgNIEXgAAShN4AQAoTeAFAKA0gRcAgNIEXgAASruw6AWcdPny5XTt4eFhqm5zczPdc39/P1X36quvpnsyzGQySdVl5ysiYmNjI1U3Go3SPbPrHfIYrGZ9fT1VN2RPycruRRH59S7iPJlaWVlJ1W1vb6d7ZvfOIftYNdl9eW1tbbYLOYWtra0z7zlvrvACAFCawAsAQGkCLwAApQm8AACUJvACAFCawAsAQGkCLwAApQm8AACUJvACAFCawAsAQGkCLwAApQm8AACUJvACAFCawAsAQGmt9z6P487loO9mZWUlVXfv3r10z2vXrqXqtre30z0XpM3puKk52d3dTTdcW1tL1z5KNjY2UnWbm5tD2s5rTiKSs3JwcJBuOB6PU3VHR0fpnlnZvSgif59fvnw53TOWbE85L4bcZ9m9c2trK90zlnBPGSK7H2X3ooj8fvTiiy+me66vr6drB3jorLjCCwBAaQIvAAClCbwAAJQm8AIAUJrACwBAaQIvAAClCbwAAJQm8AIAUJrACwBAaQIvAAClCbwAAJQm8AIAUJrACwBAaa33Po/jzuWg72ZlZeWsW8ZoNErVDVnr1tZWunaANqfjpuZkb28v3XBnZydVd3BwkO55eHh45j2zsznQvOYkYgGzcvXq1XRt1urqaqouO9cLtFR7ynkxHo/PvOeQx2As4Z4ymUxmvY6HGrKfZ+/z7PPW0NoBHjorrvACAFCawAsAQGkCLwAApQm8AACUJvACAFCawAsAQGkCLwAApQm8AACUJvACAFCawAsAQGkCLwAApQm8AACUJvACAFCawAsAQGkXFr2AWRmNRqm68Xic7rm5uZmqy651UT2XzZD77OjoKFW3vb2d7rm2tpaqq3SfLcqQWblx40aq7vbt2+me169fT9eyGLu7u6m6S5cupXseHBycaV1E/rmnmv39/XTtxsZGqu7WrVvpnuvr66m6IXvRZDJJ1c37Oc8VXgAAShN4AQAoTeAFAKA0gRcAgNIEXgAAShN4AQAoTeAFAKA0gRcAgNIEXgAAShN4AQAoTeAFAKA0gRcAgNIEXgAASruw6AXMyvPPP5+qW1tbS/e8detWqm51dTXdczQapWuJeOONN1J1R0dH6Z7r6+vpWh49Tz/9dLp2yN7AYrzwwgupuv39/XTPixcvpuqG7EX2sakrV66ka8fjcaouO2MREZPJJFV348aNdM9lzSmu8AIAUJrACwBAaQIvAAClCbwAAJQm8AIAUJrACwBAaQIvAAClCbwAAJQm8AIAUJrACwBAaQIvAAClCbwAAJQm8AIAUJrACwBAaa33vug1AADA3LjCCwBAaQIvAAClCbwAAJQm8AIAUJrACwBAaQIvAAClCbwAAJQm8AIAUJrACwBAaQIvAAClCbwAAJQm8AIAUJrACwBAaQIvAAClCbwAAJQm8AIAUJrACwBAaQIvAAClCbwAAJQm8AIAUJrACwBAaQIvAAClCbwAAJT2/19EZar26o2UAAAAAElFTkSuQmCC\n",
+      "text/plain": [
+       "<Figure size 864x864 with 5 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "# import necessary packages\n",
     "import numpy as np\n",
@@ -1589,10 +1656,17 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of training images: 1437\n",
+      "Number of test images: 360\n"
+     ]
+    }
+   ],
    "source": [
     "from sklearn.model_selection import train_test_split\n",
     "\n",
@@ -1712,10 +1786,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 5,
+   "metadata": {},
    "outputs": [],
    "source": [
     "# building our neural network\n",
@@ -1791,11 +1863,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "probabilities = (n_inputs, n_categories) = (1437, 10)\n",
+      "probability that image 0 is in category 0,1,2,...,9 = \n",
+      "[3.89940599e-05 1.79115580e-01 1.47286800e-02 7.96733555e-01\n",
+      " 3.28982767e-04 1.49752254e-07 9.19699482e-05 4.42365585e-03\n",
+      " 3.57722690e-06 4.53485505e-03]\n",
+      "probabilities sum up to: 1.0000000000000002\n",
+      "\n",
+      "predictions = (n_inputs) = (1437,)\n",
+      "prediction for image 0: 3\n",
+      "correct label for image 0: 6\n"
+     ]
+    }
+   ],
    "source": [
     "# setup the feed-forward pass, subscript h = hidden layer\n",
     "\n",
@@ -1991,11 +2078,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Old accuracy on training data: 0.16423103688239388\n",
+      "New accuracy on training data: 0.09951287404314545\n"
+     ]
+    }
+   ],
    "source": [
     "# to categorical turns our integer vector into a onehot representation\n",
     "#from keras.utils import to_categorical\n",
@@ -2095,10 +2189,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 8,
+   "metadata": {},
    "outputs": [],
    "source": [
     "class NeuralNetwork:\n",
@@ -2220,11 +2312,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy score on test set:  0.9305555555555556\n"
+     ]
+    }
+   ],
    "source": [
     "epochs = 100\n",
     "batch_size = 100\n",
@@ -2256,11 +2354,225 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  1e-05\n",
+      "Lambda =  1e-05\n",
+      "Accuracy score on test set:  0.18888888888888888\n",
+      "\n",
+      "Learning rate  =  1e-05\n",
+      "Lambda =  0.0001\n",
+      "Accuracy score on test set:  0.18333333333333332\n",
+      "\n",
+      "Learning rate  =  1e-05\n",
+      "Lambda =  0.001\n",
+      "Accuracy score on test set:  0.20277777777777778\n",
+      "\n",
+      "Learning rate  =  1e-05\n",
+      "Lambda =  0.01\n",
+      "Accuracy score on test set:  0.2\n",
+      "\n",
+      "Learning rate  =  1e-05\n",
+      "Lambda =  0.1\n",
+      "Accuracy score on test set:  0.12222222222222222\n",
+      "\n",
+      "Learning rate  =  1e-05\n",
+      "Lambda =  1.0\n",
+      "Accuracy score on test set:  0.18888888888888888\n",
+      "\n",
+      "Learning rate  =  1e-05\n",
+      "Lambda =  10.0\n",
+      "Accuracy score on test set:  0.1527777777777778\n",
+      "\n",
+      "Learning rate  =  0.0001\n",
+      "Lambda =  1e-05\n",
+      "Accuracy score on test set:  0.5916666666666667\n",
+      "\n",
+      "Learning rate  =  0.0001\n",
+      "Lambda =  0.0001\n",
+      "Accuracy score on test set:  0.5583333333333333\n",
+      "\n",
+      "Learning rate  =  0.0001\n",
+      "Lambda =  0.001\n",
+      "Accuracy score on test set:  0.5361111111111111\n",
+      "\n",
+      "Learning rate  =  0.0001\n",
+      "Lambda =  0.01\n",
+      "Accuracy score on test set:  0.5777777777777777\n",
+      "\n",
+      "Learning rate  =  0.0001\n",
+      "Lambda =  0.1\n",
+      "Accuracy score on test set:  0.6055555555555555\n",
+      "\n",
+      "Learning rate  =  0.0001\n",
+      "Lambda =  1.0\n",
+      "Accuracy score on test set:  0.6416666666666667\n",
+      "\n",
+      "Learning rate  =  0.0001\n",
+      "Lambda =  10.0\n",
+      "Accuracy score on test set:  0.8111111111111111\n",
+      "\n",
+      "Learning rate  =  0.001\n",
+      "Lambda =  1e-05\n",
+      "Accuracy score on test set:  0.8833333333333333\n",
+      "\n",
+      "Learning rate  =  0.001\n",
+      "Lambda =  0.0001\n",
+      "Accuracy score on test set:  0.9\n",
+      "\n",
+      "Learning rate  =  0.001\n",
+      "Lambda =  0.001\n",
+      "Accuracy score on test set:  0.8666666666666667\n",
+      "\n",
+      "Learning rate  =  0.001\n",
+      "Lambda =  0.01\n",
+      "Accuracy score on test set:  0.875\n",
+      "\n",
+      "Learning rate  =  0.001\n",
+      "Lambda =  0.1\n",
+      "Accuracy score on test set:  0.8666666666666667\n",
+      "\n",
+      "Learning rate  =  0.001\n",
+      "Lambda =  1.0\n",
+      "Accuracy score on test set:  0.9416666666666667\n",
+      "\n",
+      "Learning rate  =  0.001\n",
+      "Lambda =  10.0\n",
+      "Accuracy score on test set:  0.9416666666666667\n",
+      "\n",
+      "Learning rate  =  0.01\n",
+      "Lambda =  1e-05\n",
+      "Accuracy score on test set:  0.9472222222222222\n",
+      "\n",
+      "Learning rate  =  0.01\n",
+      "Lambda =  0.0001\n",
+      "Accuracy score on test set:  0.9444444444444444\n",
+      "\n",
+      "Learning rate  =  0.01\n",
+      "Lambda =  0.001\n",
+      "Accuracy score on test set:  0.9416666666666667\n",
+      "\n",
+      "Learning rate  =  0.01\n",
+      "Lambda =  0.01\n",
+      "Accuracy score on test set:  0.9333333333333333\n",
+      "\n",
+      "Learning rate  =  0.01\n",
+      "Lambda =  0.1\n",
+      "Accuracy score on test set:  0.9611111111111111\n",
+      "\n",
+      "Learning rate  =  0.01\n",
+      "Lambda =  1.0\n",
+      "Accuracy score on test set:  0.7361111111111112\n",
+      "\n",
+      "Learning rate  =  0.01\n",
+      "Lambda =  10.0\n",
+      "Accuracy score on test set:  0.3111111111111111\n",
+      "\n",
+      "Learning rate  =  0.1\n",
+      "Lambda =  1e-05\n",
+      "Accuracy score on test set:  0.11388888888888889\n",
+      "\n",
+      "Learning rate  =  0.1\n",
+      "Lambda =  0.0001\n",
+      "Accuracy score on test set:  0.10555555555555556\n",
+      "\n",
+      "Learning rate  =  0.1\n",
+      "Lambda =  0.001\n",
+      "Accuracy score on test set:  0.08611111111111111\n",
+      "\n",
+      "Learning rate  =  0.1\n",
+      "Lambda =  0.01\n",
+      "Accuracy score on test set:  0.11666666666666667\n",
+      "\n",
+      "Learning rate  =  0.1\n",
+      "Lambda =  0.1\n",
+      "Accuracy score on test set:  0.125\n",
+      "\n",
+      "Learning rate  =  0.1\n",
+      "Lambda =  1.0\n",
+      "Accuracy score on test set:  0.10555555555555556\n",
+      "\n",
+      "Learning rate  =  0.1\n",
+      "Lambda =  10.0\n",
+      "Accuracy score on test set:  0.125\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:45: RuntimeWarning: invalid value encountered in true_divide\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  1.0\n",
+      "Lambda =  1e-05\n",
+      "Accuracy score on test set:  0.07777777777777778\n",
+      "\n",
+      "Learning rate  =  1.0\n",
+      "Lambda =  0.0001\n",
+      "Accuracy score on test set:  0.07777777777777778\n",
+      "\n",
+      "Learning rate  =  1.0\n",
+      "Lambda =  0.001\n",
+      "Accuracy score on test set:  0.07777777777777778\n",
+      "\n",
+      "Learning rate  =  1.0\n",
+      "Lambda =  0.01\n",
+      "Accuracy score on test set:  0.07777777777777778\n",
+      "\n",
+      "Learning rate  =  1.0\n",
+      "Lambda =  0.1\n",
+      "Accuracy score on test set:  0.07777777777777778\n",
+      "\n",
+      "Learning rate  =  1.0\n",
+      "Lambda =  1.0\n",
+      "Accuracy score on test set:  0.08611111111111111\n",
+      "\n",
+      "Learning rate  =  1.0\n",
+      "Lambda =  10.0\n",
+      "Accuracy score on test set:  0.07777777777777778\n",
+      "\n",
+      "Learning rate  =  10.0\n",
+      "Lambda =  1e-05\n",
+      "Accuracy score on test set:  0.07777777777777778\n",
+      "\n",
+      "Learning rate  =  10.0\n",
+      "Lambda =  0.0001\n",
+      "Accuracy score on test set:  0.07777777777777778\n",
+      "\n",
+      "Learning rate  =  10.0\n",
+      "Lambda =  0.001\n",
+      "Accuracy score on test set:  0.07777777777777778\n",
+      "\n",
+      "Learning rate  =  10.0\n",
+      "Lambda =  0.01\n",
+      "Accuracy score on test set:  0.07777777777777778\n",
+      "\n",
+      "Learning rate  =  10.0\n",
+      "Lambda =  0.1\n",
+      "Accuracy score on test set:  0.07777777777777778\n",
+      "\n",
+      "Learning rate  =  10.0\n",
+      "Lambda =  1.0\n",
+      "Accuracy score on test set:  0.07777777777777778\n",
+      "\n",
+      "Learning rate  =  10.0\n",
+      "Lambda =  10.0\n",
+      "Accuracy score on test set:  0.07777777777777778\n",
+      "\n"
+     ]
+    }
+   ],
    "source": [
     "eta_vals = np.logspace(-5, 1, 7)\n",
     "lmbd_vals = np.logspace(-5, 1, 7)\n",
@@ -2293,11 +2605,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 720x720 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 720x720 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "# visual representation of grid search\n",
     "# uses seaborn heatmap, you can also do this with matplotlib imshow\n",
@@ -2355,11 +2686,486 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  1e-05\n",
+      "Lambda =  1e-05\n",
+      "Accuracy score on test set:  0.20833333333333334\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  1e-05\n",
+      "Lambda =  0.0001\n",
+      "Accuracy score on test set:  0.16944444444444445\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  1e-05\n",
+      "Lambda =  0.001\n",
+      "Accuracy score on test set:  0.18055555555555555\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  1e-05\n",
+      "Lambda =  0.01\n",
+      "Accuracy score on test set:  0.17222222222222222\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  1e-05\n",
+      "Lambda =  0.1\n",
+      "Accuracy score on test set:  0.23333333333333334\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  1e-05\n",
+      "Lambda =  1.0\n",
+      "Accuracy score on test set:  0.2916666666666667\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  1e-05\n",
+      "Lambda =  10.0\n",
+      "Accuracy score on test set:  0.1527777777777778\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  0.0001\n",
+      "Lambda =  1e-05\n",
+      "Accuracy score on test set:  0.8666666666666667\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  0.0001\n",
+      "Lambda =  0.0001\n",
+      "Accuracy score on test set:  0.8416666666666667\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  0.0001\n",
+      "Lambda =  0.001\n",
+      "Accuracy score on test set:  0.9277777777777778\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  0.0001\n",
+      "Lambda =  0.01\n",
+      "Accuracy score on test set:  0.8861111111111111\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  0.0001\n",
+      "Lambda =  0.1\n",
+      "Accuracy score on test set:  0.8805555555555555\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  0.0001\n",
+      "Lambda =  1.0\n",
+      "Accuracy score on test set:  0.875\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  0.0001\n",
+      "Lambda =  10.0\n",
+      "Accuracy score on test set:  0.875\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  0.001\n",
+      "Lambda =  1e-05\n",
+      "Accuracy score on test set:  0.9833333333333333\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  0.001\n",
+      "Lambda =  0.0001\n",
+      "Accuracy score on test set:  0.9833333333333333\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  0.001\n",
+      "Lambda =  0.001\n",
+      "Accuracy score on test set:  0.9805555555555555\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  0.001\n",
+      "Lambda =  0.01\n",
+      "Accuracy score on test set:  0.9861111111111112\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  0.001\n",
+      "Lambda =  0.1\n",
+      "Accuracy score on test set:  0.9805555555555555\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/MortenImac/anaconda3/lib/python3.7/site-packages/sklearn/neural_network/multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
+      "  % self.max_iter, ConvergenceWarning)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate  =  0.001\n",
+      "Lambda =  1.0\n",
+      "Accuracy score on test set:  0.9805555555555555\n",
+      "\n",
+      "Learning rate  =  0.001\n",
+      "Lambda =  10.0\n",
+      "Accuracy score on test set:  0.9527777777777777\n",
+      "\n",
+      "Learning rate  =  0.01\n",
+      "Lambda =  1e-05\n",
+      "Accuracy score on test set:  0.9861111111111112\n",
+      "\n",
+      "Learning rate  =  0.01\n",
+      "Lambda =  0.0001\n",
+      "Accuracy score on test set:  0.9916666666666667\n",
+      "\n",
+      "Learning rate  =  0.01\n",
+      "Lambda =  0.001\n",
+      "Accuracy score on test set:  0.9861111111111112\n",
+      "\n",
+      "Learning rate  =  0.01\n",
+      "Lambda =  0.01\n",
+      "Accuracy score on test set:  0.9833333333333333\n",
+      "\n",
+      "Learning rate  =  0.01\n",
+      "Lambda =  0.1\n",
+      "Accuracy score on test set:  0.9944444444444445\n",
+      "\n",
+      "Learning rate  =  0.01\n",
+      "Lambda =  1.0\n",
+      "Accuracy score on test set:  0.975\n",
+      "\n",
+      "Learning rate  =  0.01\n",
+      "Lambda =  10.0\n",
+      "Accuracy score on test set:  0.9416666666666667\n",
+      "\n",
+      "Learning rate  =  0.1\n",
+      "Lambda =  1e-05\n",
+      "Accuracy score on test set:  0.8861111111111111\n",
+      "\n",
+      "Learning rate  =  0.1\n",
+      "Lambda =  0.0001\n",
+      "Accuracy score on test set:  0.875\n",
+      "\n",
+      "Learning rate  =  0.1\n",
+      "Lambda =  0.001\n",
+      "Accuracy score on test set:  0.9194444444444444\n",
+      "\n",
+      "Learning rate  =  0.1\n",
+      "Lambda =  0.01\n",
+      "Accuracy score on test set:  0.9361111111111111\n",
+      "\n",
+      "Learning rate  =  0.1\n",
+      "Lambda =  0.1\n",
+      "Accuracy score on test set:  0.9\n",
+      "\n",
+      "Learning rate  =  0.1\n",
+      "Lambda =  1.0\n",
+      "Accuracy score on test set:  0.825\n",
+      "\n",
+      "Learning rate  =  0.1\n",
+      "Lambda =  10.0\n",
+      "Accuracy score on test set:  0.6777777777777778\n",
+      "\n",
+      "Learning rate  =  1.0\n",
+      "Lambda =  1e-05\n",
+      "Accuracy score on test set:  0.10555555555555556\n",
+      "\n",
+      "Learning rate  =  1.0\n",
+      "Lambda =  0.0001\n",
+      "Accuracy score on test set:  0.10555555555555556\n",
+      "\n",
+      "Learning rate  =  1.0\n",
+      "Lambda =  0.001\n",
+      "Accuracy score on test set:  0.18888888888888888\n",
+      "\n",
+      "Learning rate  =  1.0\n",
+      "Lambda =  0.01\n",
+      "Accuracy score on test set:  0.14722222222222223\n",
+      "\n",
+      "Learning rate  =  1.0\n",
+      "Lambda =  0.1\n",
+      "Accuracy score on test set:  0.08611111111111111\n",
+      "\n",
+      "Learning rate  =  1.0\n",
+      "Lambda =  1.0\n",
+      "Accuracy score on test set:  0.11388888888888889\n",
+      "\n",
+      "Learning rate  =  1.0\n",
+      "Lambda =  10.0\n",
+      "Accuracy score on test set:  0.10555555555555556\n",
+      "\n",
+      "Learning rate  =  10.0\n",
+      "Lambda =  1e-05\n",
+      "Accuracy score on test set:  0.15833333333333333\n",
+      "\n",
+      "Learning rate  =  10.0\n",
+      "Lambda =  0.0001\n",
+      "Accuracy score on test set:  0.08611111111111111\n",
+      "\n",
+      "Learning rate  =  10.0\n",
+      "Lambda =  0.001\n",
+      "Accuracy score on test set:  0.21944444444444444\n",
+      "\n",
+      "Learning rate  =  10.0\n",
+      "Lambda =  0.01\n",
+      "Accuracy score on test set:  0.058333333333333334\n",
+      "\n",
+      "Learning rate  =  10.0\n",
+      "Lambda =  0.1\n",
+      "Accuracy score on test set:  0.1111111111111111\n",
+      "\n",
+      "Learning rate  =  10.0\n",
+      "Lambda =  1.0\n",
+      "Accuracy score on test set:  0.1\n",
+      "\n",
+      "Learning rate  =  10.0\n",
+      "Lambda =  10.0\n",
+      "Accuracy score on test set:  0.10277777777777777\n",
+      "\n"
+     ]
+    }
+   ],
    "source": [
     "from sklearn.neural_network import MLPClassifier\n",
     "# store models for later use\n",
@@ -2388,11 +3194,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 720x720 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkIAAAJgCAYAAABmwww9AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAAIABJREFUeJzs3Xd4FFXbx/Hv7G4qIdQkVBVEpCMgUhRQFBFRASuKD7yCIErHRxEVu6iAIoogVUCqSEfEICgWQkex0BXpCRggQNqWef9YniQDQRCSXTb7+1xXrisze3bm3HtmZs/ec86uYZqmiYiIiEgQsvm7AiIiIiL+oo6QiIiIBC11hERERCRoqSMkIiIiQUsdIREREQla6giJiIhI0FJHSOQy9MYbb9CmTRvatGlDjRo1aNmyZdZyenr6v96eaZr83//9HykpKecs8/vvv3PttdcyYcKES6m6iEhAMfQ9QiKXt+bNmzNixAhq1qx50dtwuVxUr16ddevWER0dnWuZQYMGkZaWxsaNG1m2bBl2u/2i9yciEigc/q6AiPx7O3bs4M033yQlJQW3283//d//0a5dO06ePMnAgQPZs2cPNpuNmjVr8uqrrzJw4EAAOnTowPjx44mLi7Ns78SJEyxevJh58+bRvXt34uPjadWqFQBOp5MhQ4bw3XffYbfbuf766xk0aBBArutHjhxJamoqL7zwAgDDhw/PWn744YcpWbIku3btokOHDlSpUoX33nuPjIwMDh8+TNOmTXn99dcBWL58OSNGjMA0TQoVKsRrr71GfHw8e/bsYciQIQCsXbuWd955hzlz5vjkdReRgkcdIZEA43Q66dOnD++99x5VqlQhJSWFBx98kEqVKrF9+3YyMzNZsGABLpeLl156iX379vHWW2+xcOFCpk2blmtGaP78+VxzzTVcddVVtGvXjsmTJ2d1hKZOncq2bdtYuHAhISEh9O3bl6VLl3LkyJFc159PsWLFWLJkCQB9+vShX79+XH/99Zw8eZLmzZvToUMHihUrxoABA5g6dSpVqlThyy+/5L333uO1116jVatWpKSkEB0dzaxZs2jfvn3evsAiElTUERIJMLt27WLv3r0MGDAga11mZiZbtmyhYcOGjBgxgo4dO9K4cWO6dOlC+fLlcblc/7jNGTNm8OijjwLQpk0b3n//fTZv3kytWrVYtWoVbdu2JSwsDIAPPvgAgK5du+a6fvjw4f+4r3r16mX9P3ToUFauXMno0aP5448/yMjI4NSpU/zxxx9UrVqVKlWqANCqVausjlmTJk1YtGgRrVq1YvXq1bzxxhsX/NqJiJxJHSGRAOPxeChatCgLFizIWnf48GGio6MJCwtj2bJlrFmzhtWrV9OpUydefvllbrnllnNub82aNfz555+MGTOG8ePHAxAaGsrkyZN59913sdvtGIaRVf7IkSN4PJ5zrjcMg5xDD51Op2V/hQoVArwDuNu3b0+NGjVo0qQJrVu3ZtOmTZimicNhvTR5PB62b99OlSpV6NChA2+99RYul4tWrVoRERFxEa+iiIiXZo2JBJhKlSphs9n44osvANi/fz933XUXW7du5dNPP2XQoEE0adKEZ599loYNG7Jjx46sTktumaHp06fTrl07Vq5cyYoVK1ixYgUfffQRS5cuJTExkcaNG7No0SIyMzPxeDwMGjSIpUuXnnN98eLF+e233zBNk1OnTrFq1apc4zh69Chbt27lmWeeoUWLFuzfv599+/bh8Xi47rrr2L59O7t27QIgPj4+a5xT/fr1cTqdTJ48WbfFROSSKSMkEmBCQ0MZPXo0gwcP5uOPP8blcvH0009Tu3Ztrr76atatW0fr1q0JDw+nbNmyPProoxiGwW233cZDDz3Exx9/zNVXXw14M0nLly+3ZJcAbrrpJmrUqMHUqVPp06cPBw8e5N5778U0TRo1akSHDh0wTTPX9SdPnuSHH37g9ttvp1SpUtSpUyfXOIoXL06XLl1o06YNRYsWpUSJEtSpU4e//vqLG264gSFDhvDMM8/gdrspXLgww4YNy3ruvffey/Lly6lUqVL+vdAiEhQ0fV5EAorT6eTJJ5/kgQceoGXLlv6ujogEON0aE5GAsXXrVho3bkzx4sVp0aKFv6sjIgWAMkIiIiIStJQREhERkaCljpCIiIgELXWEREREJGgF5PT5W1q+4+8q+E3o32n+roJfmY7g7rvb0pznL1RApV2R+4/FSnAI/WKtv6vgV8s8s326P8+hyj7bl63Udp/tK9f9+3XvIiIiIn4UkBkhERERyT8ePD7bl78zMv7ev4iIiIjfKCMkIiIiFm7Tdxkhf3dElBESERGRoKWOkIiIiAQtf2ekRERE5DLjIXh+fUsZIREREQlaygiJiIiIhS+nz/ubMkIiIiIStJQREhEREQu3qTFCIiIiIgWeMkIiIiJioVljIiIiIkFAGSERERGxcCsjJCIiIlLwKSMkIiIiFhojJCIiIhIElBESERERC32PkIiIiEgQUEZIRERELILnl8aUERIREZEgpo6QiIiIBC3dGhMRERELfaGiiIiISBBQRkhEREQs3MGTEFJGSERERIKXMkIiIiJioenzIiIiIkFAGSERERGxcGP4uwo+o4yQiIiIBC1lhERERMTCo1ljIiIiIgWfMkKnNbyhIo8/1oyQEDt//HmYocO/JDU101LmtubVaP9AA0zTJD3DxYejvmb7jkMAjBnZidBQBy6XG4CvV/zOrM/X+jyOi3XDjdfwWM/bCAm18+eORIa/vpDUUxm5ln365bb8tSuJz6euAqBwdAS9nmtNxWtLkZ7mJH7RJhbOCpzYz3RD42vo/FRzQkLs/LkziffeXHjWsXDrHTW5v0MjMCE93cmo95ayY+tBP9X40t3QpDKP9W5BSKiDP7cfYvgr88/d/q+1Y/fOJOZM+RGAF4a1p0z54lmPlypbjF827OaVPtN8UvdL1fD6inTr2NR77u8+zDsfLCU1zdreLW6uRvt762OakJHh5IOxy9m2MxGApo0r8+gDDQgJsZOYlMLg4UtIOZHuj1AuyqXE37tbc2pVL59VLqZEFH8nn6Jz70k+juLi3XBnXboMfoSQsBD+3PwX7z4+mtQTaRdcZnbiBP7en5xV9rNhC1gx/QefxpAfgmmMkGGaZsAlwG5p+U6ebq9IkQg+GduFXv2msf/AUbp1aUZkRCjvj1yWVaZ8ueIMH/Iw3XpOIjn5FA3qV6Rf75a0/89owsNCmD39Kdo++CFud/5OOgz9O+38hf6lIkUjGftZD/p1mcCBvcl06XUbEZFhjHznC0u58leVpOeA1lSpWY5PP/4mqyP031fa4nZ7GPHmImw2Gy+/257Fs9ex5ofteV5X05G/ScwiRSMZN/1J+j7xife16HErkZGhfDj0y6wy5a4owdBRHenRaRzJf5+kfqNK9BnQmkfbjsjXugHY0px5vs0ixSIZM7cX/TuN48CeZDr3vZ2IyFA+GrzYUq58hRh6PH+Xt/1HrcjqCOVUuXpZXhjWnqf/bxxHElPytJ5pV0Tn6fYAikRHMPmjx+jx7HT2HzzGE52aEhkZyvDRX2eVKV+2GCMGt+fxvlNIPnqKBvUq8HSP23mw8xiurRTHW4Pu5alnpnEoKYUej99CWKiD90Yt+4e9Xj4uNf6cSsVG8+HbDzPw9Xns/DMpz+sa+kXef7gqUjKacb++R7+bXmT/zkM8/nYHIgpH8GGP8RdUplzlMry+cACPVemT53U70zLP7HzfR06/7y3rs31VK7/fZ/vKjc9uje3atYtRo0bx0ksv8corrzBq1Ch++eUXX+3+H9WvW4Ft2w6x/8BRABYs3sStzatbymQ6XQx7/0uSk08BsG37IYoXK4TDYaNKldKkpTl56/X7mfBxZ556ojmhoYGTbKvb8Gq2/b6fA3u9n2oWf76e5q1qnlXungdvIH7RJr5b9ptl/TVVy7B8yWY8HhOXy83aH7Zz063VfFL3vFavQUW2bTmQ/VrMXU/zltbXwul0MXzwYpL/PgnAjq0HKFYiCkc+d9LyS91Gldj+634O7PHG/MVna2l+Z+2zyt3d/gaWLdjI9/G/5rodh8PO06/fy5ihS/K8E5Rf6te5iq07DrH/4DEAFnz5E7c1sx67TqebIR9+RfLR0+f+zkSKF/We+y1ursYXy37hUJI33knTf2TGnMDJhl5q/Dk907Mlny1Yny+doPxS7/ZabF+3i/07vZn9RaPjufWRJhdcpnrjynjcHoYuf5kxPw3j0UH3Y7MF5nXgTG4Mn/35m09abNq0afTv3x+AmjVrUr26t5MxaNAgJk6c6Isq/KOYmMIkHcm+cB8+fIKoQmFERoZmrUtMTGH12j+ylp96ojmrVu/E5fIQGRHKpp//4pU35tO912TiYqPp2rmZT2O4FDFxRSxvXIeTUigUFU5koTBLuY+GLGH5ks1nPX/rr/u49c5a2O02wiNCual5NYqXjMr3eueHmNgiHE48nrWc9VrkPBYOHmftqh1Zy0/0uZ3V32/D5QrMryCLKXVGzIkpFCp8dvuPeusLli/++ZzbadmuLsmHT7BqxZZ8q2tei40pTNKRE1nLh4+cPvcjstv7UFIKq9dnn/s9utzCj2u95375ssWx2228+UJbJnzQib7dW5x1W+lydqnx/0+DehWIiSnMnEUbfVPxPBJTviSH9x3JWj68728KFYkksnDEBZWxOexs+Hozz7d6k/7NXuL622vTptcdPo1BLp1P0hZTpkxh/vz5REREWNY/9thjtGvXjs6dO/uiGudks+XeI/Xk8mMr4WEhDPjvncTGRPPsC58BsGr1Tlat3plVZtqMBF59qR0ffbw8fyqcx84V/4Xe5hs7PJ6ufW9n1PTuJB85wcY1u6hWq/z5n3gZMs51LOQyhSI8PIT/DmpDTFw0z/cNjPEwuTGMc7S/59917Nr9pzEfvLYgL6rkM7ZzxJ5re4eFMLBvK2JKFubZVz4HwGG30fiGq+n/wmccPX6K7o/dzDO9WvLim/Pztd555VLj/58H2lzP9M/X5Pq8y9m5r/2eCyrz5fjsa7wz08XnwxfTrtedzBuxJG8r6gce0/+ZGl/xSUbI4XDgcrnOWp+enk5ISIgvqvCPEpNSKFE8O4MRU7IwKSfSSM+wjseIjSnMyPcfxeMx6ffsDE6dHkzaqMHV1KpRLrugYeT7WKG8lHTouCWDUzKmMCeOp5GRfmHjUSILhTHhg2U88dAoBvb4FNM0ObAv+fxPvAwdTjxO8ZKFs5ZLxkSTcjyN9DNei5i4aIaPewyPx8MzPaZw6mTuA4sDweFDZ8QcW5gTx1PJ+Bfjka6uUhq73cbm9bvzoYb5J/HwCUoUK5S1XLLEuc/9j4Y+gtvjoe8Lszh5+tw/knySdRt3k3zsFKYJX379C9WvLePTGC7FpcYP3nFGVSuX5tt8GBOY35L2HKF4qWJZyyXLFicl+STpqRkXVOa2R5tSoeYVWY8ZhoHLefZ7nVzefNIR6t69O23btuXFF19kxIgRjBgxghdffJEHHniA7t27+6IK/2j9ht1UrVKGsmW8B/vdra/jx4SdljKFC4fz/rBH+O6H7bz+1kIyM7MP9piYwnTvdguhoQ5sNoMH76vPNysD5/bAhtW7qFKjXNbMn9b3XU/Cyq0X/Py77ruejt1vAaBo8UK0aluPb5ZeHuO//q0Na3ZRtUbZrNfirnb1SPh+m6VM4ehw3h3diR+/3crgQXPJzAjsC9+GhJ1UqVWeMlecbv8HbiDh2wtvf4Ca9a7i5xy3jgPFuk27qXZtGcqWLgrAPa1q8+OaM879qHA+eKs9363awWtDF1vO/ZU/bqfh9RWJLhwOQNNGldl6eixJILjU+AFqVivL1h2Hzuo8BYIN8T9TteE1lK1UCoC7ut9OwoJ1F1zmqhrl6fTqQ9hsNkLDQ2nT4w6+/WyVb4OQS+azWWOJiYkkJCSQlJSEaZrExcXRqFEj4uLi/vW28nrWGECD+hXp2rkZDoedAweP8tbQLyhdqijP9LuDrk9NosPDjXjsPzfx5+7Dluc9PWAmJ06m063LzTRqUAm73eCnn/fwwaivcTrdeV7P/Jg1BlD/xmvo3ONWHCF2Du47ytCX51GqbDH6vXgPT3X42FL2zOnzEZGhPPvavZQpXxwDmDnpB1Z8efZYoryQ37PGAOo3qpQ1ff7AvqMMfW0+pcoUo//zd/Nkx7E8/H830bHrzezeZR0U+mzPTzmRkj/t8z/5MWsMoP5N1/BY79tPt38yQ1+YQ+lyxej7clt6PDTKUvbM6fMAPQbeRfKRE8wYtzJf6gf5M2sMvONbunVqSojDzv5Dxxj83hLKlCrCM73u4PE+k3n0wYZ0fuRG/vjriOV5/V+cRcqJdNq0uo62ra/DZhgkHk7hnQ+W8vfpSRWB4FLjb9+uPuXLFWfoh1/laz3zY9YYwA2t6tB58COEhDo4sCuRIZ1GUrpiLP3HPUn3us+cs8yJoycJiwil58guVG1QGUeIne8+T2DiCzPypZ6+njW2cc8V5y+UR+pescdn+8qNps8HmPzqCAUKX3SELmf51REKBPnVEZLAkF8doUChjlD+CZw53iIiIuIT7iD64YngiVRERETkDMoIiYiIiIWmz4uIiIgEAWWERERExOJy+OkLX1FGSERERIKWMkIiIiJi4TaDJ08SPJGKiIiInEEZIREREbHwBFGeJHgiFRERETmDMkIiIiJioVljIiIiIkFAGSERERGx0KwxERERkSCgjpCIiIgELd0aExEREQuPBkuLiIiIFHzKCImIiIiFO4jyJMETqYiIiMgZlBESERERC02fFxEREQkCygiJiIiIhX50VURERCQIKCMkIiIiFm5T3yMkIiIiUuApIyQiIiIW+h4hERERkSCgjJCIiIhYePQ9QiIiIiIFnzJCIiIiYqExQiIiIiJBQB0hERERCVq6NSYiIiIW+kJFERERkSAQkBmh5z6e7O8q+M0hV1F/V8GvbHj8XQW/uiIk2d9V8Js9zuL+roJfxTpS/F0Fv0p5P8LfVQgq+tFVERERkSAQkBkhERERyT9ufaGiiIiISMGnjJCIiIhYeNCsMREREZECTxkhERERsdAYIREREZEgoIyQiIiIWOhHV0VERESCgDJCIiIiYuHRb42JiIiIFHzKCImIiIiFxgiJiIiIBAF1hERERCRo6daYiIiIWHj0hYoiIiIiBZ8yQiIiImLh1o+uioiIiBR8ygiJiIiIhcYIiYiIiAQBZYRERETEQmOERERERIKAMkIiIiJioTFCIiIiIkFAGSERERGxcCsjJCIiIlLwKSMkIiIiFh7NGhMREREp+JQREhEREQuNERIRERG5zCxatIg777yTFi1aMG3atLMe/+2337jvvvu45557eOKJJ0hJSTnvNtUREhEREQuPafjs70IlJiYyfPhwpk+fzoIFC5g1axY7d+60lHnzzTfp3bs3CxcupEKFCkyYMOG829WtMREREfGblJSUXDM30dHRREdHZy2vWrWKhg0bUrRoUQBatmzJ0qVL6dmzZ1YZj8fDqVOnAEhLS6NIkSLn3b86QiIiIuI3kydPZuTIkWet79mzJ7169cpaTkpKIiYmJms5NjaWzZs3W57z3HPP8dhjjzF48GAiIiL47LPPzrt/dYRERETEwu3DkTOdOnWiXbt2Z63PmQ0CME3zrDKGkX1rLT09nRdeeIHJkydTq1YtPvnkEwYMGMDYsWP/cf/qCJ322xqTRZ94cDmhTAV4uJ+NiELWe5c//2jy5aceDBtERMHDfW3ElDE4dcLksw9N9u8yCQ2HBrcbNGsTWMOvdq7L5JvJqbidJrFXOWjdpxBhkdYYtq3K4LvpaRgGhEcZtO4dRbHSdgA2fJHOT/HpuDKgVCU7rftE4QgJnO+h2LHOyTeT03A5TeKusnNXn0KERVrrv3VVJt9NT88RfyTFT8e//ot0forPxJlhUrqSg7v6RAZU/DltXgPzPgGXE8pWgE79IKKQtcyKBfDNQggJhdJXwCM9oFB07tu73AV72wf7tW/bWhfxkzJxO03iKtho1zec8DPa//dVLpZPzTwdv0HbPmGUKG1jxptp/H0w+8356CEPFWraefTlCF+HEdDOvAV2LnFxcaxfvz5rOSkpidjY2Kzl7du3ExYWRq1atQB46KGHGDFixHm3G1hHbD45ccxk2nseOg+y8eIEOyVKGyz6xNrzzMww+XSIhy4v2Rgwyk7NhgZzRnsAmDfGJCwcnh9ro//7NrasN/l1zdk918vVqeMeFr9/kvsGFqb7mGIULWXjm0mpljLODJOF757kvucL8/iHRancIJT4Md77sFtXZbB+UTqPvBFNt1FFcGXC2vnp/gjlopw67mHR+6e4f2AhnhpThKKlbKyYlGYp48wwWfDuKe5/vhBdP4ymcoMQ4sd4X6OtqzJZtyiDDm9E0X1UNK5MkzXzM/wRyiU7cQwmvwvdB8HrEyCmFMydaC2z9SdY+hn0fxteGg016sOn57/WXJaCve117TOZOzyDh18Ip++4QhQvZSP+E2v7OTNMZg9N55EXw+k5MpIqDex88bG3zMMvRNBzZCQ9R0bStncY4YUM7noqzB+h5LnLcbB048aNSUhIIDk5mbS0NOLj42natGnW41deeSWHDh3ijz/+AGD58uXUrFnzvNtVRwjYutHkisoQW9bbIDe1Nli/wrSk4UwPmECa972fjDTvp2GAvTtM6t9qYLMbOEIMqtU3+On7wLkY/LnRSelrHBQv6/2EW/fOcH77NjPX+DNSvesy00wcod7X69cVGTRoF05EYRuGzeCOHoWoeUuoz+O4WH9sdFLmGntW/PXuDOPXbzMuOP7NKzJpmCP+Vj0iAyr+nH7fCFdeC3FlvcvN7oI1KyBnRnrPDqhaB4qdvlVf9yZvFsnl9H19L1Wwt32wX/t2bHRRtrKNkmW9b4U3tA7h529clvg93j4f6af+1/7gCLFux+U0mfNuOq2fCKNojN5W80tcXBz9+vWjY8eOtG3blrvuuotatWrRtWtXfvnlF4oUKcJbb71F3759ufvuu5kzZw6DBw8+73Z1aww4dhiKxWT3SovGQHqq9+9/twTCIgwe6mUwvL+HQoW9F4e+73kP+CuvNVi33KRide+bwc8/mtjt/ojk4qQc8RBdMvvkjS5pIyPVJDPNzLpFEBph0OqpKKb89zgR0QYeD3Qc4h2N//d+D6Ure5j5Ugonkj2Ur+6g+WOFct3X5SjliJlL/N4LXlikd11ohMGdT0Uy6b8niIg2MD3QaUhhAJL3uzlV2c70l05wMtmkfHUHtz4WmKnx5MNQvGT2crEYSE81SE81s86Fq6rA8gXwdyKUiIMfvwKX0+BkiknREv6p98UK9rYP9mvf8cMmRUpmxx9d0iAj1dvZCz/d/mERBvf0DGPs02lEnr72dRtmbeMN8S4Kl7BRrXHBeUv1XKZ5krvvvpu7777bsm7cuHFZ/zdr1oxmzZr9q236JNIDBw7845+/5TL+CgBbjhP6wJ8mS6eZPD/GxhvT7dze3mDC6x5M06RtNwMMGNLDw/jXPFxbx8Aekvs2L0e5DUADMGzZF4ik3S5+mJlKt9FF6T2lODc+GMHcwScwTROPy+TPTU7aPRdF5+FFSD9hsnJKaq7bvBydO/7s/5N2u/l+ZjpPjI6m75Si3PhgOJ8PPoVpmrhd8OcmF/c9F0WX4YVJO+Hh2ylpuW7zcmd6cl+f81yoXBPufhRGvQZv9gSbDQoVNs/6lBwIgr3tde3Lfb0tR/sf+tPNN9Mz6T0mkgFTC3HzQyHMeDPdcuysmpfJze0DKHCx8En39YknnmD37t3ExsaedeExDIPly5f7ohrnVCwGdm/NrtfxIxAZBWHh2R2BLRtMKlY3iCnjXdfkboO5Y01OpUBmBrR53KBQYe/Zs+wzT1a5QFAkxs6Bba6s5RN/ewiPMgjNEf8fG52UqxqSNTi6Xutwvh6fSlqKSVQJG9c2Cs0aXF3jljB+mBE4bwZFYmwc2ObOWk7JJf5dG52Uq+rIGiB7feswlo1PIy3FpHAJG9c2CsnKntW8JYzvAyj+nIrHwp9bs5ePHYHIKO84kP9JT/V2hm66w7ucchQWTIZChX1b17wQ7G0f7Ne+ojEG+7Zlx59yxCQiCkv779zo5opqdkqU9sbY4K4QlozLJDUFChWBA7vceDxQoWYApcIugPtfjN0JdD7JCM2YMYMKFSowZMgQVqxYYfnzdycIoEo9g7+2QtJ+7wnxwxcmNRtZD4LylQx2bjZJOeotsznBe1sgqojBj1+YLJniXZ9y1CThS5N6NwfOQVShTgj7t7lI3u99Q9i4JJ3KDa3jHEpd7WDPr05OHvWmDLavzqRonI3IIjaq3BjKlh+8s2ZM02R7Qialrwmci0LFs+LPpHJD66e7Ulfb2fOrKyv+baudWfFXvTGELT84s+LflpBJmWsCM0VerR78sRUS93uXV34B1zWyljn2Nwx7NnvMyOJpUP9mMALnkM8S7G0f7Ne+SnXt7N3q4ch+b9uuW+KkSkNr+5W+2sbuX9xZ7b8lwU2xOINCRbxx7v7FTcVadss0bgkshnmu3HAe27x5M7Nnz+b111+/5G199We1PKiR1W9rvVNI3S4oWRoefcbG3wdhxvseBozyvql/t9DD94tM7A6ILAwPPGWj9FXe8ROfDvVw5IA31driIYP6t+ZPH/OQq2i+bHfnuky+nZyK2wXFStu4u38Uxw55+OKDkzz+oXef6xens2FxOnYHhBc2aNm9EDFXOvC4TX6clcbv32diekxKXe2gVc+zp9/nBRvnuHdziXauc7Jichpul0mx0nba9I/k6CEPX3yQStcPvdM61y9OZ93iDOwOg4jCBnd0jyTmSjset8kPs9L5/ftMPB7vG2frnmdPwc4LV4Qk5/k2z/TLWpg3EVwuiCkNnZ+Bw4dgynDvLDHwTp//dpH3eK9UHR7uAaH5PFlmj7N4vmw3UNo+1nH+30y6GIFy7Uvx5M/Yq23rXCyblInbZVK8lI37/hvO0YMe5n2QQc+R3oFCqxdlsmaxM6v973oylLgrva/Noo8yiCpucMvD+TtI/oGrN+Tr9s+8qzo8AAAgAElEQVTUZ9PDPtvXiDozfLav3PisI5SX8qMjFCjyqyMUKPKrIxQofNERulzlV0coUORXRyhQ5FdHKFCoI5R/AieHKyIiIj7hMS/PWWP5IXgiFRERETmDMkIiIiJi4SZ4Bn8rIyQiIiJBSxkhERERsfg3vwEW6JQREhERkaCljpCIiIgELd0aExEREQtNnxcREREJAsoIiYiIiIVH0+dFRERECj5lhERERMTCrenzIiIiIgWfMkIiIiJioVljIiIiIkFAGSERERGx0E9siIiIiAQBZYRERETEQt8jJCIiIhIElBESERERC40REhEREQkCygiJiIiIhb5HSERERCQIqCMkIiIiQUu3xkRERMRCg6VFREREgoAyQiIiImKhL1QUERERCQLKCImIiIiFxgiJiIiIBAFlhERERMRCGSERERGRIKCMkIiIiFgoIyQiIiISBAIyI3RzeLq/q+A3GeY+f1fBr0IMu7+r4Fe2IPpujzPdEJbo7yqIH6WaKf6uQlBRRkhEREQkCARkRkhERETyj75ZWkRERCQIKCMkIiIiFhojJCIiIhIE1BESERGRoKVbYyIiImKhW2MiIiIiQUAZIREREbFQRkhEREQkCCgjJCIiIhbKCImIiIgEAWWERERExMJURkhERESk4FNGSERERCz0o6siIiIiQUAZIREREbHQrDERERGRIKCMkIiIiFho1piIiIhIEFBGSERERCw0RkhEREQkCKgjJCIiIkFLt8ZERETEQoOlRURERIKAMkIiIiJiocHSIiIiIkFAGSERERGxME1/18B3lBESERGRoKWMkIiIiFh40BghERERkQJPGSERERGx0PcIiYiIiAQBZYRO+y7BYMQ4O5lOqFzR5NVn3UQVspaZPtfGjHk2wkOhwpUmL/R1UyQa3G4YPMLGhp+9/cqbGnh4+kkPRgB1qH9IsPHR+BAynXBNRZMXn8k8K/5Zc+18Nt9BWChUuNLDs32cFImGAS+Hsnd/drAHDhnUre3hvTczfRzFxfsuweDDcXYynQbXVDR55VnXWfHPmGtj5jw7YaEmFa80GZij/d8eYbe0f78n3QHV/sF+/Adz+wdz7AA/Jtj5eHwoTidcXdHD889kUOiM+GfPdTBnfghhoSZXXmny3z4ZREd7H5sz38GiJQ4yMgyurex9fmio7+PIa/oeoSCTfAwGvWPnvddcLPrURbkyJu+Ptb40azcZTJxuY9y7LmZPcNGkoYdXh9kBWBxvsHuvwZyJ3sc2/GywbGXgHERHj8FrQ0J559VM5kzJoGxpDyPHhljKrN9kY8qMEEa9m8H08Rnc2MDD4He9Z/s7r2Yyfbx3/Qv/zaRwlMmzfZz+COWiJB+Dl99xMOw1Fws+dVKujMmIsXZLmXWbDD6Zbmfsu04+m+DipoYmrw/zfo5YHG9j916D2ROdzJrgZH2AtX+wH//B3P7BHDt4r31vDglj8KvpzJySRpnSHkaNtfZiNmyyMXVGCB+8m87k8ek0auDm7XfDAPj2Ozufzwvhg2HpTPskjcwMmPl5SG67ksuYOkJAwjqDGlVMriznXX7wHg9LvrZZvkfh920GDeuZlIr1Lt/axGRlgoHTCW4PpKVDphOcmeB0GQH1iWD1OjvVrvVwRTlvwPe1cbN0ud0S/5btNurXcxMX412+pYmb7xNsOHP0d5xOePXtUPr3cFIqNnC+hCJhnY3qOdr/gXvcfJlL+zeo5yEuq/09We3vOaP9XS4IC6D2D/bjP5jbP5hjB1i7zk7Va92UP33tu7eNi/jlDkv8205f+2JjvCtvbuLixwQ7Tid8Ge/g4QedREeDzQbP9M+gVQuXP0LJc6bpuz9/81lH6Ouvv+bTTz9lz549lvWzZs3yVRXO6VCSQamY7NaIi4GTpwxOpWaXqVHVZO0mgwOHvMsLvrThdBocS4E2d5hER8Ft9ztofp+D8mVNbm58GbTuBUo8bBCXo+MSG2Ny6oz4q1fxsH6TjYOHvJ/2Fi2143QaHE/JLrNgiZ2SJUxuaeLxVdXzRGISF9T+6zbZcm3/e+7wEB0Ft98fwm33hVC+LDQLoPYP+uM/iNs/mGMHSDxss1z7Yk5f+1JzxF+1iocNm+xZ174vljpOX/sM9u6zcfSoQb9nw/hPlwgmTAolKipw4hcvn3SEhg0bxtSpU9m9ezft27dnwYIFWY/NnDnTF1X4R55zHLe2HK/O9bVNundy03eQg/bd7Bg2KBJtEuKAjyfbKF4Uvp3nYtlsFykpMHlW4CTbzHP0W+w5Qqhb20PXji6eeSmUjk+EYRje+B05RpnN+NxBl/8E3qehc7V/zvjr1TZ5opOb/oMcPNLNYWn/MZPtFCtqsmKek69mOzmeAlMCqP2D/fgP5vYP5tjh3Ne+nMd+ndoeOnd0MvClMDo/EY5hQHS0SYjDxOWCdRvsvPFyBhM/TiPlhMGYCQGUEvsHpmn47M/ffHLErly5kvHjxzNo0CCmT5/OiBEj+PLLLwEwL4O8WOlYk8PJ2Y2RdASiC5tERmSXOZXqfTP4bJyLmWPdtGjqPYOKRMPX39loe6eHkBAoHAX3tPSwbpP/G/dCxcWZHPk7u76HDxtEFzaJOCP+utd5mDo2gyljMmje1A144wfYtsPA5fZ2mAJN6Vg4kkv7nxl/vdoeZo5zMX2si9tytP/y7wxL+9/d0sO6TYHzZhDsx38wt38wxw4QF+c569pXOJf461znZtLYdCaOSeeWpt4Pe9HRULKESdObXBQqBCEh0PI2F7/+Fjjxi5dPWsw0TYzT0wiuuuoqxowZw5tvvsmaNWuy1vtTo/omm383+Gufd3n2Qhu33GjtoCUdgc59HZw85V0eM8VGq+bemTFVK5t89Y03DqcLvl1lo1Y1/3fwLlTD6938usXGnn3eGOYsstP0RrelzOEjBt37hmXFP+HTEG5vnj07ZMPPNurXCayZQv/TqL7H0v6fL7Rz843WDt3hI/B435Cs+MdOsXNHjvaP/8Z7KjldsHKVjVrVAqdDGOzHfzC3fzDHDnDD9W5+22Jn7+lr3/xFDprcaM1qHzli0KNvOKdOx//Jp6G0aO7CMOCWZi6+WekgI8M71uW7H+1UrRI48YuXYfogJTNy5EhWrVrFc889R61atQDYsGEDPXv2JDMzkw0bNvyr7WUcrJjndfx+tXf6sNMJ5cuYvPm8m30HDF4Zamf2BO+JMWOujZnzbXhMqFvTZGAfN+FhcOw4vPWBnS3bDex2aFDXw9NPeQjJhy8nyDDz59bTj6ttfDQuBKcLypUxeWVgJvsPGrwxNJTp4zMA+GyendnzHXhMuK6Gh2f6OAn3Tp7gnfdDKFnCzPdbYyGG/fyFLsL3q71TiJ1Og3JlTN543sW+AwavDrXz2en2nznXxqz5djwm1Knp4bkc7f/2B3a2brdhs5s0qGvS/yl3vrS/LZ++9j4Qjn8P+XepCpT2zw+BEnuqmT8zUVettvPxuBCcLoOyZTy8NDCD/QdtvD00lMnj0wH4fJ53+rxpQq0abp7uk0lYmPfrAyZNDWH5Nw48Hqh8jYcB/c+efp8XSpTZl/cb/Qc1F77ss339cs+rPttXbnzSEQJISEggNjaWq6++OmvdwYMHmThxIi+88MK/2lZ+dIQCRX51hAJFfnWEAkV+dYQCQX52hOTyl18doUChjlD+8dlnlkaNGp21rnTp0v+6EyQiIiL5S1+oKCIiIhIEAuQutoiIiPjKZTCh22eUERIREZGgpYyQiIiIWFwOX3ToK8oIiYiISNBSRkhEREQslBESERERCQLKCImIiIhFEE0aU0ZIREREgpcyQiIiImKhMUIiIiIiQUAZIREREbEKokFCygiJiIhI0FJHSERERIKWbo2JiIiIhQZLi4iIiAQBZYRERETEwtRgaREREZGCTxkhERERsdAYIREREZEgoIyQiIiIWCkjJCIiIlLwKSMkIiIiFpo1JiIiInKZWbRoEXfeeSctWrRg2rRpZz3+xx9/8J///Id77rmHLl26cPz48fNuUx0hERERsTJ9+HeBEhMTGT58ONOnT2fBggXMmjWLnTt3ZlfZNHnyySfp2rUrCxcupGrVqowdO/a821VHSERERC57q1atomHDhhQtWpTIyEhatmzJ0qVLsx7/7bffiIyMpGnTpgB0796dDh06nHe7GiMkIiIiFr78HqGUlBRSUlLOWh8dHU10dHTWclJSEjExMVnLsbGxbN68OWt5z549lCxZkgEDBvD7779TuXJlBg0adN79KyMkIiIifjN58mRuvfXWs/4mT55sKWfmMoLbMLI7bC6Xi7Vr1/Loo4+yaNEiypcvz9tvv33e/SsjJCIiIlY+nDXWqVMn2rVrd9b6nNkggLi4ONavX5+1nJSURGxsbNZyTEwMV155JTVr1gTgrrvuonfv3ufdvzJCIiIi4jfR0dGUK1furL8zO0KNGzcmISGB5ORk0tLSiI+PzxoPBFCnTh2Sk5PZunUrACtWrKB69ern3b8yQiIiInLZi4uLo1+/fnTs2BGn08n9999PrVq16Nq1K71796ZmzZp89NFHvPjii6SlpVGqVCmGDBly3u0aZm433S5zGQcr+rsKfpNhuvxdBb8KMez+roJf2Qier70/k8eXuXq57KSaTn9Xwa9KlNnn0/1d9en5x9bkld3/ec5n+8qNbo2JiIhI0NKtsQATZQv3dxX8Ks3M8HcV/CrMCPN3FfwmI8gzAsHugNvfNfCvEr7eYRAlYJUREhERkaCljJCIiIicIXjGIyojJCIiIkFLGSERERGx0hghERERkYJPGSERERGxUkZIREREpOBTRkhERESsTM0aExERESnwlBESERERi8D7FdKLp4yQiIiIBC1lhERERMRKGSERERGRgk8dIREREQlaujUmIiIiVpo+LyIiIlLwKSMkIiIiFoYGS4uIiIgUfMoIiYiIiJUyQiIiIiIFnzJCIiIiYqVZYyIiIiIFnzJCIiIiYqUxQiIiIiIFnzJCIiIiYqWMkIiIiEjBp4yQiIiIWCkjJCIiIlLwKSMkIiIiVvoeIREREZGCTx0hERERCVq6NSYiIiIWhgZLi4iIiBR8ygiJiIiIVRBlhNQROu27BIMR4+xkOqFyRZNXn3UTVchaZvpcGzPm2QgPhQpXmrzQ102RaHC7YfAIGxt+9ibYbmrg4eknPRgBNOj+2wQYPhYynXBtRXhjAGfFP3UOTJsH4WFQ8QoY1A+KRsOxFHj1Pdi6EyLC4d5W8Oh9/onjYn2fYOPDcQ6cTrimoslLzzrPin/mXDuz5tkJO93+z/V1UiQannkphL37sxv7wCGDurU9vD/Y6eMoLl6wt/93CQYfjrOT6TS4pqLJK8+6zop/xlwbM+fZCQs1qXilycAc5//bI+yW87/fk+6AOf+DOXaADavtTJsQissJV1T08NTTGUSeEf+SeQ6WLgghNMyk7BUmj/fKoHA0nDoJo98NY/9eG6YHmt3uol37wDnvxUu3xoDkYzDoHTvvveZi0acuypUxeX+s9aVZu8lg4nQb4951MXuCiyYNPbw6zA7A4niD3XsN5kz0PrbhZ4NlKwPnSpB8DF54G0a8Dl9OhXJl4N0x1jJrNsL4GfDJezBvAjRtCC8P8z729kiIjIDFk2HmaPhuDXyzyvdxXKyjx+CVd0IY9pqTeZ9mUraMyYdjrZ8R1m2yMWm6g4/fzWTmhExubOjmjWEhAAx9zcnMCd71g55xEhUFz/UNnIthsLd/8jF4+R0Hw15zseBTJ+XKmIwYa7eUWbfJ4JPpdsa+6+SzCS5uamjy+jDvMbI43sbuvQazJzqZNcHJ+gA6/4M5doDjx+CjYWE883I6H0xKI660h2njQy1lfv3JxvxZIbw8NJ1hY9Kpe4ObMcPDAJg5KZQSMSbDx6fx9kdpxC9ysO13va0GGp+12O7du0lMTARg9uzZvPHGGyxZssRXu/9HCesMalQxubKcd/nBezws+dqGmSM1+Ps2g4b1TErFepdvbWKyMsHA6QS3B9LSvZ+mnZngdBmEhp69n8vVj+ugRhW46nT8D7eBxV9jif+37dCoHlnxt2jqfbPLdHofa3M72O0QGgLNGkH8St/HcbES1tmoXsXDFeW8AT9wj5svv7Zb4t+yzaBBPQ9xWe3v4bsEG84c/R2nE156K4T/9nRmvU6BQO1vo3qO89/b/mef/2e2///Of88Z57/LBWEBcv4Hc+wAP2+wU6mym9Knz/2Wd7v4frnDEv+u7TZq1XVTIsa7ssFNLtavtuN0QucemXR8IhOAo8ne1ySyUBDdUyogztsRmjhxInXr1qV27dq0atWKvn37Mnr0aFasWMG+ffsuaCeTJk2iS5cutG/fnoEDB/LFF19QoUIF5syZw0cffXTJQVyqQ0kGpWKyD964GDh5yuBUanaZGlVN1m4yOHDIu7zgSxtOp8GxFGhzh0l0FNx2v4Pm9zkoX9bk5saBczIcSoLSOd64c4u/ZlVvVmD/6fjnfUlW/LWqwoJ4cLrgVCosWwmH//ZtDJciMckgLkf7x8aYZ8VfvaqHdZtsOdrfnhX//8xfYiemhEnzJh4f1TxvqP25oPPf2v7Z5/89d3iIjoLb7w/htvtCKF8WmgXI+R/MsQP8nWSjRGx2fUvEmKSmGqTliP+aKh5+3WTncKI30/XNVw5cToOTKQaG4f0AMOKtMPo/HkH12h7KlAuc+P+JYfruz9/O2xEaM2YMQ4YMYdmyZbzxxhs0aNCAxMRExo0bR9u2bbn++ut5+OGH/3Ebc+bMYcmSJUydOpWlS5cyZswYOnTowOjRo/nqq6/yLJiL5TlHQ9hyvDrX1zbp3slN30EO2nezY9igSLRJiAM+nmyjeFH4dp6LZbNdpKTA5FmBkx71nON9O2f89WvDU/8HvV6E+7uBYWTHP+Ap7/K9j3sfb3w9hATQ6LNztb89R/z1apt06+Tiv4NC6dAtFFuO9v+fabPtPP4fd/5WNh+o/XNff2b7P9HJTf9BDh7p5rCc/2Mm2ylW1GTFPCdfzXZyPAWmBMj5H8yxw4Vd+6vV8vBARydDXg7j2afCMQyIKmzicGQ/uc/ADCbOTeVkCnw+NSSfay157byXq6ioKG6++WYcDgexsbHUq1fP8vi+ffvYsWPHP27D4/EQGhpK2bJl6dy5M2FhYVmPud3+f+MoHWvyy5bsIz/pCEQXNomMyC5zKtXbGbq3tQuAv5Pho4k2ikTD19/ZGNjHTUgIhITAPS09LFtpo9NDvo7k4pSOg81bspcTj0CRXOKvXxvub+1dPpIMH0z0DpY9mAT/7e79H2DcdLiinO/qf6lKxZr8mkv7R5wRf93aHtq29h6vfyfD6IkOipyOeesOA7cb6l0XWNkgUPuXjoVft2SPazlX+9er7aFda2/7/p0MoybaKRINy78zeC7H+X93Sw9fr7TR8aHL/1gI5tgBYmI97NiS/TaYfMQgqrBJeI7401KhWi03t7byXvuPHfWODYqKhp/W2bmigofiJb2v2U3N3az+3n7mbgKTfmIjW7du3Zg9e/Y5Hy9Xrhy33HLLP27j9ttv59FHH8XtdtOrVy8Atm7dyiOPPEKrVq3+ZZXzXqP6Jpt/N/jr9J2+2Qtt3HKj9aNC0hHo3NfByVPe5TFTbLRq7p0ZVrWyyVffeA8apwu+XWWjVrXLIN93gW6sDz//DrtPxz9rITS/0Vom6Qh06ktW/KOnQOtbvZmAWQvgw4ne9UeS4fPFcNetvqv/pWpU38Mvv9vYs8/bhnMWOmh2o7WDfviIQbe+oVnxj5vioGXz7NkxG36yUb9OYM0U/B+1v8dy/n++0M7NN1rfyA8fgcf7hmTFP3aKnTtynP/x33gvpU4XrFxlo1a1wOgIBHPsALXrudmxxc7B0+d+/CIH9Ru7LGWS/zZ4+elwUk/H//nUUG5q7sIwYNVKO7M/DcE0vWOkVq20U+M6/3+4l3/HME3zH9+x69Spg9PppGnTpjRp0oSqVaty7bXXEpHzI8MFWLduHfXr189a/uOPP9i7dy/NmjX715XOOFjxXz/nfL5f7Z0+73RC+TImbz7vZt8Bg1eG2pk9wXtizJhrY+Z8Gx4T6tY0GdjHTXgYHDsOb31gZ8t2A7sdGtT18PRTnny5PRBi5M89h5WrvdOnnU4oXxbefh72HYBBQ72zhACmzYXp8zgdPwzq651KfSoVBrwJf+33DrDt1gHuuT1fqkmamZEv2/1hdfb0+XJlTF5/3sn+AwavDQ1h5gTvYMiZc+18Nt87iPq6mh4G9HERfjq5+db7DmKKmzzeMX8vghFG2PkLXYRAaP8MM/9m4n2/2juF3Ok0KFfG5I3nXew7YPDqUDufnT7/Z861MWu+HY8JdWp6eC7H+f/2B3a2brdhs5s0qGvS/yl3wNweDJTYd7ryp/03rrEzbUIILpdBXGkPvQZkkHjQxsfvhTJsTDoAX853sHRhCKYHqtRw06VXJmFh3unzY94PY+9uGwZQ/0YXD3VyWm6t5ZWa5S9sTG5eqfj+ez7b1x99+/tsX7k5b0do7969bN26lW3btrFt2za2bt3KgQMHKFeunN/G9+RHRyhQ5FdHKFDkV0coUORXRygQ5GdHSC5/+dURChTqCOWf876rli9fnvLly9OiRYusdampqWzfvj1fKyYiIiJ+EjijOy7ZRSXwIiMjue666/K6LiIiIiI+Fdz3WUREROQsl8P3+/hK4Hzhg4iIiEgeU0ZIRERErJQREhERESn41BESERGRoKVbYyIiImKlW2MiIiIiBZ8yQiIiImKh6fMiIiIiQUAZIREREbEyDX/XwGeUERIREZGgpYyQiIiIWGmMkIiIiEjBp4yQiIiIWGjWmIiIiEgQUEZIRERErJQREhERESn4lBESERERC40REhEREQkCygiJiIiIlTJCIiIiIgWfOkIiIiIStHRrTERERKx0a0xERESk4FNGSERERCw0fV5EREQkCKgjJCIiIkFLHSEREREJWhojJCIiIlYaIyQiIiJS8CkjJCIiIhaaNSYiIiISBAIyIzTnVIy/q+A3x9yR/q6CX208caW/q+BXLYr+5u8q+E0px3F/V8Gvwg2nv6vgV+MO3+bvKvjV+PI+3qEyQiIiIiIFX0BmhERERCQfKSMkIiIiUvApIyQiIiIWmjUmIiIiEgTUERIREZGgpVtjIiIiYqVbYyIiIiIFnzJCIiIiYqHB0iIiIiJBQBkhERERsVJGSERERKTgU0ZIRERErJQREhERESn4lBESERERC80aExEREQkCygiJiIiIlTJCIiIiIgWfMkIiIiJipYyQiIiISMGnjJCIiIhYaNaYiIiISBBQR0hERESClm6NiYiIiJVujYmIiIgUfMoIiYiIiIUGS4uIiIgEAXWERERExMr04d+/sGjRIu68805atGjBtGnTzlnu22+/pXnz5he0Td0aExERkcteYmIiw4cPZ+7cuYSGhtK+fXsaNGhApUqVLOWOHDnCO++8c8HbVUZIRERErHyYEUpJSWHfvn1n/aWkpFiqtGrVKho2bEjRokWJjIykZcuWLF269Kyqv/jii/Ts2fOCQ1VGSERERPxm8uTJjBw58qz1PXv2pFevXlnLSUlJxMTEZC3HxsayefNmy3OmTJlCtWrVqF279gXvXx0hERERsTB8uK9OnTrRrl27s9ZHR0dblk3z7AFFhpFd0+3btxMfH8+kSZM4dOjQBe9fHSERERHxm+jo6LM6PbmJi4tj/fr1WctJSUnExsZmLS9dupTDhw9z33334XQ6SUpK4pFHHmH69On/uF2NERIRERGry3DWWOPGjUlISCA5OZm0tDTi4+Np2rRp1uO9e/fmq6++YsGCBYwdO5bY2NjzdoJAGaEs29c6WT45DbcT4q6yc0/fSMIircnBLasy+XZaOoYBEVE27u4TQfHSdgDWLc5gY3wmrgyT0pW8z3eE+DK5eGn+XJfOj1NScLtMSl4Zwm29ixIWae0n70xIY/X0Exg2CI+ycWvPohQtbT2EFg9OplBxG7d0L+rL6l+y5E1H+XPWHkyXh0LlI7mm69U4IrNjS/z+MPuXHMhadqW5yUzO5IYP67Lzkz9JT0zPeiz9cAZFqkZT/ekqPo3hUmxb6+TryRm4nFDqKhtt+kYQfsbx//sqJ99My8AwIDzKoG2fCIqXtjFzcCrJBzxZ5Y4meriqhoMOL0f6Oow8sXkNzPsEXE4oWwE69YOIQtYyKxbANwshJBRKXwGP9IBC5/9Ae1n6aY3B7Il2nE6D8hVMHu/vOive+Pk2vl5oJzTUpMwVJh17uonKEe/fSfBanxDe+NhJ4SK+rf+lCvZzP5DExcXRr18/OnbsiNPp5P7776dWrVp07dqV3r17U7NmzYvarmHmdtPtMjd9Z4M83d6p4x5GPXmCzkOjKFHWzrKJaWSmmbTukX0hd2aYDH34ON1HFqZ4GTsJ89L58ycXj7waxZYfM1kxJZ3Ow6IIL2Qw+61Uylxj56YHw/O0ngDH3Hn/5pJ63M3Unod54J2SFCvj4IdJKWSmeWj+ZHZnxpVhMubRQ3QYEUPRMg42LjjJ3p8zaPNSiawy6+ecYOO8U1xzU3i+dYQ2nrgyz7eZmeJk44CfqP1yDSJKRfDnjL9wp7up9FjFXMt7XB42v/4bcU1jKX1rnOWxE7tOsmXENmq/XIOwEmF5XtcWRX/L822eOu5h5JOneHxoJCXK2omfmE5GmsndPSKyyjgzTN5++ARPjYyiRBkbq+ZlsOsnN/951Xo87t/uZubgVB4fWogiMXmbcC7lOJ6n28vNiWPwSjd4djjElYU54yE9DTpkj9dk608wcSgMfB+KxUDC1/BzAnQflL91Czeceb7NlGMwsGsIg953UqoszBpvJy0V/q+3O6vM7z8ZjBni4OURTorHwI9f29i4ykavl1wA/LDMxtwpdo4kGnw0OzPfOkLjDjfL8wTpQ30AACAASURBVG0G0rk//vpJeb7Nf1K773Cf7evn9/v5bF+58cutsbffftsfuz2nXRtdlL3GTomy3uzO/7d353E21u8fx99nNmOMmTFmsaSkJlNCiKzJVrKEUCKyli+ytkpRyFqDlNL2JUokhWQpkWVaFb5lixJmxowZs5n9nPP74/gNd0OmzNzHzP16Ph7z4L7PfeZc19z3uc91rs/nPqdhRx/t3ZJjmJjldLg6eFlnXOtysiQvH9c75t2bc9Tk3jIqW95DNg+bOo4oqzqtfUzP49/686dshUd4q0IV17ugOnf76cDWTEP+DodTckrZGa53/rmZTnme1/E6tidbR3dlq3b7ktcFSN6bLP8a/ipbyfXCX7ltuOJ3nLrgxDxJOr4mRt4B3gVOhI48hw68/ptq9K1eLCfC4vLbLruq/OX437Ml9y/73/Vv9nnHv/dfDvG8XKc+fjlTdz/sW+RFkFl+3SVdU9NVBElSy07St5ul8w+FPw9JN9ZzFUGSVL+5q4uUV/R1SrH7348eqlHTqUpn823dya7ozR6GfP84ZFOteg4Fn8331mYO/fStTXm50ulE6cedHho3pQQmL577cCn2obGnn366wLrNmzcrJcX17m7atGnFHcIlpSY4FHDeiTsgxEPZGVJOplTm7Ou6T1mbOg330zuPpatsgE1OhzRwlr8kKfGEQ2eSnVrybLrSkhy6upaX2g0se6GHuiKlnbLLP8Qzf9k/xFM5GU7lZDrzhwd9ynqo9bBArXjilHwDPOSwS/fNCJEkpSfatfXNFHV7vqL2rj/jlhwuR3ZijsoEnzt5lQkuI3umXfZMu6FFLkm5abk6sS5G9abWKfB74rbEq0wFH4U0rFjgtitZSoJDgaHnitqAEJuyM6TsTMn37PFfpqxNnYf76s3HzsgvwCaHQxo8yzh+smtjrsoH23RTU28zwy9SSQlScMi55QqhUlaGTVkZzvzhouqR0pefSoknpYrh0o4NUl6uTempTgWVrF2vxAQpOPTci35wqJSZYVNWxrnhwBo1ndr4iadOnbQrJFz6eqPH2XylChWlURPz3BT95bP6c/9vlbixon+v2N+2BQUFacuWLYqMjFSjRo3UqFEj+fn55f//SnCxwUHbeX+dk3/YtfWDLA17vbzGvReoFvf7avmLZ+R0OuWwS0d+ylPPp8vp4TnllZXm1ObFmeYEXwScjguv9zgv/1N/5OrbZWl68NUwDf5vJTW6z1+fTU+SPc+pz2edVsvBgSoX7HnhX3SFu9i7P5tHwTlesZtPKrhBsHzDCg57xnweq2pdqxZ5fMXtYse/x1+O/y0fZOvR1/31+Hvl1fJ+Hy17McPwt4v+JEcte5Xsd8MXfS6cd2jfUFvq/KD02gvS1BGuv1O58k55lcD6rzD7PrKOU90etGvu8156briXbDZXvp4lMN+/svpzHy7FXgg9+eSTevnll7Vu3TpVqVJF3bp1U2BgoLp163bBzw1wh8BQD6UnnTsDpiY65etvk4/vuSfD4R9zdfVNnvmToxt29FH8UYcyU50qH2xTZFNvlfGzydPbptqtfHR8n73A41ypAkI9lXFe/umJdpXxt8nb99zhcfSnbFW50Sd/cnSdDuWU+Gee4g7kKDU+T1+/k6Klo+K1d32GDm3P0hevJJuex7/lW7GMcpJz8pezk3LkVc5Tnr4FC7tT3yQqvGVogfXpf5yR0+5U4I0lb8ZsUKhN6UnnXhDSEp0q6y/D8X/oxzxdfZOXgiu7jolGZ4//jFTX/WIP2+WwO1W9dskshv9fcJiUknRuOfmU5OfvVJnzXvuyMlzF0LOvSs/Mdw2NSVK58ubGWhQqhkrJSef28+lTriKnzHkN7cwMKbKOQ5Nfy9MLr+apYQvXucK/BOb7V1Z/7sPFlIH8Jk2a6I033tD777+vGTNmyG6/soqE6+p76fgBuxJPuOL6YV22Ihsb3+5Uvt5Tf+zNU/pp10lg/ze5Cgr3kF+gh25s5qNft+coN9spp9Op/d/kqsoNJecF4ep6ZRR7IEenY1wt7r2fZ6jGbcZ3PWE1vHX8lxydOe36Gx3+NksBYZ6qWquMBr1TSX3mhqnP3DDVbu+niOa+avtoyblqLKh2kNJ+S1dmnKuLF/tlnCo2CC6wXe6ZPGWezFJARMFXgJR9qQqsFWj4cK+S4rr6Xjp23vH//bqcAsd/lb8c//u+yVOFcJvKBbpOIb/vzdO1db1KZP7nu6mBdGS/dPKEa3nrZ9ItTYzbJCdKs5+QMs+OAq9dKjW8QyqJqddu4NDhfTbFnc1381pP1W9ibIslJ0ovPu6dn++nSz3VpJWjROb7V1Z/7v+tK/Dy+eJi2uXzQUFBmjt3rlasWKEDBw6Y9bCFUi7IQ11G+2nFtDOy50oVKnuo2zg/xRzK0+q5GRo6P0DX1vVW0+6+WvRUujy9XZfP93rWNYjesKOPMtOdWjgqTU6HVPk6T901uORMGvYL8lS7UUFaNz1J9jwpsJKn7hpTQScP5eiL+cnqMzdM1eqWUYNu/lr5TKI8vSTf8h7qPKHgCaMk8gn01g2PXKd9cw/KkedU2bAyuuE/1yvtSLoOvXlY9ae5Pqo9Ky5LPkHe8vAq+P4hMy5TviElc1jIP8hD3Ub7atk018dHBFf20L3jyurEIbs+nZupYfP9VaOul5p1L6N3nso4e/zb1PvZc8d4UoxDQeElc4L0+QKCpP7jpDcmS3l5UmhlaeDj0h8HpcVR0nMLpErVpPb3SdNGuYaWrq8lPTDc3ZH/OwEVpCGP5emVyV7Ky7UprIpTjzyepyMHbXrnZU9NeT1PlatJne63a9JIbzmd0g21HOo34sp6M/tvWf25Dxcuny9hiuPy+ZKkOC6fL0mK4/L5ksKMy+evZMVx+XxJUhyXz5ckZl8+f8uj5l0+//MrFrx8HgAA4ErAJ0sDAACjEjdW9O/REQIAAJZFRwgAABjY6AgBAACUfnSEAACAER0hAACA0o+OEAAAMGCOEAAAgAXQEQIAAEZ0hAAAAEo/OkIAAMCIjhAAAEDpRyEEAAAsi6ExAABgwOXzAAAAFkBHCAAAGNERAgAAKP3oCAEAAAOb0zotITpCAADAsugIAQAAI+s0hOgIAQAA66IjBAAADPgcIQAAAAugIwQAAIzoCAEAAJR+dIQAAIABc4QAAAAsgI4QAAAwoiMEAABQ+lEIAQAAy2JoDAAAGDBZGgAAwAJKZEfo3Yc6uzsEt/E6HOPuEOBG/1VDd4fgXoEB7o7AbXIqWzd3SfLZf9zdIbhXnMmPR0cIAK4wFi6CABSfEtkRAgAAxYc5QgAAABZARwgAABg5rdMSoiMEAAAsi44QAAAwYI4QAACABdARAgAARnSEAAAASj86QgAAwMDmcHcE5qEjBAAALIuOEAAAMGKOEAAAQOlHIQQAACyLoTEAAGDAByoCAABYAB0hAABgxJeuAgAAlH50hAAAgAFzhAAAACyAjhAAADCiIwQAAFD60RECAAAGzBECAACwADpCAADAiM8RAgAAKP3oCAEAAAPmCAEAAFgAHSEAAGBERwgAAKD0oxACAACWxdAYAAAwYLI0AACABdARAgAARg7rtIQohM5q1OR6DRraSt4+Xvr9t5N6adpaZWTkGLZpc+fN6tm7iSSnsrJy9dqcjTq4Pzb/9nL+ZfTyq/300rS1hvUlQcO2N2vA+C6u/Ped0JwxS5SRnnXBbcfO7auj+2O1csEXhvUhVSoo6rPHNbzNVKUmnTEj7CJD/tbNv2HLmhowrr0r9wOxmjN+pTLOZF9w27HTeurooTitfGdb/rpl0RN06mRq/vLKt7/WV2t+Lva4i8ptja/T4CGt5O3tqSNH4jV75mcFzn1t29XSffc3llNSdlau5r+yUQcPxMnLy0OPjrxLtetUkyR99+1hLXxjsxwl6EXUysc+XBgakxQY5KfHnumsF575SAMfWKDYmGQN+k9rwzZXXR2sIcPbaPy4DzS0/1t6f9F2TZzaI//2Rk2u0/w3B6raNSFmh3/ZAiv6a+ycvpoyaKGGNH9ecUdPacCErgW2qxZRSdM+GqUWnRsUuK1Nz9s0+9OxCqkcZEbIRYr8rZt/YIVyGjutp6Y8ukRD2r+kuGNJGvBY+wLbVasRqmmLhqjF3bUN66teG6K0lEyN6Dov/6ckFUGBgX56/MlOmvTcSvXv94ZiY5I1+OFWhm2uqhash4e20VNPLNMjg9/Wkvd2aNIL3SVJXbvdqsAgPw0asFCDB72pWjdXVcs7bnRHKv+KlY/9S3Ka+ONmphRCe/bsyf9/dHS0pk+frtmzZ2v37t1mPPwlNWhUQwf3xejE8dOSpDWrflSbO282bJObY9fL0z9TUmK6JOngvlhVqOgvLy/Xn7Brj0aaOWW1Ek+lmRt8Eajf8kYd/PmoYn5PkCStXfS1Wt3bsMB2nQbcrk3LorVtzY+G9cHhgWrSvq6e6/OqKfEWNfK3bv71m0fo4N7jijmaKEla+8G3atW5XoHtOvVpok0f/6Btn+81rL+p3jVyOJyavniIXls9Sr2Ht5GHh82U2IvCrQ2v1YH9sTpxwnXuW716l9q0rWXYJjfXrpdmfaaks52OgwdiFRzsOvd9tOI7TX5+lZxOKTDAT+X8fZWWlml6Hv+WlY99nGPK0NjEiRO1atUqLV26VMuWLVP37q53E88995x69uypBx980IwwLio0LEAJ8eda2wkJqSrn7ys/P5/8FvHJuBSdjEvJ3+aRke0Uvf2g8vIckqTx4z4wN+giFFKlghLOnggl6VRMssoFlJWfv6+hRbxg/HJJ0i0tahrun3QyRVMGLTQn2GJA/tbNP6RSoBLikvOXT8WlqFx5X/mVK2MYHlswebUk6ZbG1xvu7+npoZ92HNLbM9fJx9dbzy/sr4z0LH2yaIc5CVym0LAAJSQYz33+lzj3/Wd4W0XvPJR/7rPbHRr88B3q2u1WHTgQq717jpmbxGWw8rF/KVw1VkyWL1+uxYsXq3///urfv7+WLl2qJUuWmBnCBV3sHdyFxrl9fb317OR7VfWqCnp5+triDs0UF8vf7nCYHIl7kL9187/c3Nev+F6vT12j3Fy7zqRladW729X0Lx2VK5mH7Z+d+56b1E1VqlbQ7FmfGW57a+EWden0sk7GpWj0mIJDi1cqKx/7OMeUQigvL08Oh0MVK1aUn59f/nofHx95eLh/mlJ8XIqCK/rnL4eEBCg1NVNZWbmG7ULDAzTn9f6yO5x6bMQSnUm/8ITKkib+xGkFhwfkL4dUDlLa6TPK/suEydKK/K2bf3xssoJDz8s9PEBpyRnKzsz9m3ud07pLPVWvWSl/2WaT8vLsRR5ncYmPT1Fw8PnnvvIXPPeFhQVo3vx+cjicGjd6af65r9bNV+mqq4IluTpDG9bv0fU3VFJJYeVj/5KcTvN+3MyUKqRChQpq2bKlfvvtN02cOFGSa65Qr1691L69+989/PjdEd1Yq6qqXlVBktSpW31Fbzto2KZ8eV+9NL+ftm/drxcnrlJOTp47Qi0Wu7b+qsgG16rKtaGSpA79Wih6w55L3Kv0IH/r5r9r+yFF1q2mKtdUlCR16HWbor/8tdD3rx4Rrr4j28nDwyafMl7q3Kepvl5Xcv52P3z/u266qaqqVnWd+zrfU187dxQ8970890Ft23ZAU174xHDuq1fvGv1neFt5eNpks0lt2tbSz7uOmprD5bDysY9zTJkjtHjxYknSkSNHlJrqGo/28fHRyJEjdccdd5gRwt9KTs7Q7BfX6NkpPeTt7amYE6c1c/KnuiGyssY+1VFD+7+lzt0aKCw8QM1b1lTzlufGiR8fuVRpqSVncuCFpJxKV9To9/TMW0Pk5e2l2KMJmv3oIkXUvVqjXuqjEW2nuTvEYkX+1s0/JemMop7+SM/Me1Be3p6K/TNRs59croibq2rUlO4a0XXe395/6fwvNey5LlqwZrQ8vTy1bf1erV/xvUnRX77k5AzNnLFWE5+/15V/zGlNf3GNbqhZSeMe76hHBr+tzl3qKywsQM1b1FTz8+bIPD72fS37IFrDRrTTm28NlsPp1P/2Htdbb37lxoz+GSsf+5dipTlCNqfzCuhL/UPtmk1xdwhu43U4xt0hAO4RGHDpbUqxnMrWzt9n/3F3h+BWn8e9ZurjtbprhmmP9dWGJ017rAvhAxUBAIBRiWuR/Hvun6kMAADgJnSEAACAga3kzZr51+gIAQAAy6IQAgAAlsXQGAAAMLLQh2vTEQIAAJZFRwgAABgwWRoAAMAC6AgBAAAj6zSE6AgBAADroiMEAACMmCMEAABQ+tERAgAABjbrNIToCAEAAOuiIwQAAIyYIwQAAFD60RECAAAGNr5rDAAAoPSjIwQAAIyYIwQAAFD60RECAABG1mkI0RECAAAlw5o1a9ShQwe1a9dOS5cuLXD7F198oS5duuiee+7RsGHDlJKScsnfSSEEAACueCdPnlRUVJTef/99ffrpp/rwww/122+/5d+enp6uSZMmaeHChVq9erVq1qypV1555ZK/l0IIAAAY2JxO034Ka+fOnWrcuLGCgoLk5+enu+66S+vXr8+/PTc3V5MmTVJ4eLgkqWbNmoqNjb3k72WOEAAAcJvU1FSlpqYWWB8QEKCAgID85fj4eIWGhuYvh4WFac+ePfnLFSpUUNu2bSVJWVlZWrhwofr27XvJx6cQAgAARiZePr9o0SLNnz+/wPoRI0bo0UcfPS+kgjHZbLYC69LS0jRs2DBFRkaqW7dul3x8CiEAAOA2Dz300AULlvO7QZIUHh6uH374IX85Pj5eYWFhhm3i4+M1aNAgNW7cWOPHjy/U41MIAQAAIxO/YuOvQ2AX07RpU73yyitKSkpS2bJltXHjRk2ePDn/drvdrqFDh+ruu+/WsGHDCv34FEIAAOCKFx4erjFjxqhfv37Kzc1Vjx49VKdOHQ0ZMkQjR45UXFycfv31V9ntdm3YsEGSdPPNN2vq1Kl/+3sphAAAgME/uZrLTJ07d1bnzp0N6958801JUu3atbV///5//Du5fB4AAFgWHSEAAGB0hXaEigMdIQAAYFklsiPk+b8j7g7BbRwRV7s7BLfySMtydwjulVLwQ8cs40yGuyNwK58Dae4OAVZCRwgAAKD0K5EdIQAAUIxM/Bwhd6MjBAAALIuOEAAAMLhSP0eoONARAgAAlkUhBAAALIuhMQAAYMTQGAAAQOlHRwgAABjREQIAACj96AgBAAAjOkIAAAClHx0hAABgxFdsAAAAlH50hAAAgAFfsQEAAGABdIQAAIARHSEAAIDSj44QAAAwctARAgAAKPXoCAEAACPmCAEAAJR+FEIAAMCyGBoDAABGDI0BAACUfnSEAACAER0hAACA0o+OEAAAMOIDFQEAAEo/OkIAAMDI6XB3BKahIwQAACyLjhAAADDiqjEAAIDSj44QAAAwstBVY5YuhBrdWUcDJnaXdxlv/f7LMUWNeFcZaVmF2sbDw6Zhsx9U7WY1JUnfb9qjtyYslyTVaRGpwZPvk5eXp7KzcrTgifd1cNfvpuf3TzRqFqEBI9rK28dTvx86qajJq5VxJvuC246b2FVHD8froyU7JUnlA8rq0ac6qkbNSsrKzNXGNT9p9YffmRn+ZWvYsqYGjGsvbx8v/X4gVnPGr7xo/mOn9dTRQ3Fa+c62/HXLoifo1MnU/OWVb3+tr9b8XOxxF5WGbW/WgPFdXPnvO6E5Y5YoIz3rgtuOndtXR/fHauWCLwzrQ6pUUNRnj2t4m6lKTTpjRthFomHrmzTg6c5nc4/RnMc+uHjuL/fR0QOxWvnGZkmSj6+3hk/pqYhbrpaHzaYDPx3VqxNWKCcr18wULkvDNrWM+37s0ovnP6evju6P0crXvzSsD6kSpKi1j2t42xdL1L6XrH3sw8WyQ2OBFctr7GsDNbnvqxp863jF/pGgAZN6FHqbNr2a6qqISvpPk2c1rNlE1WlWUy263iovb0+Nf3eo5o78r4Y1n6gPZq3VEwuHuCPFQgsM8tO4iV01+YkPNbj7fMWdOK2BI9oW2K5a9RDNWPCQbm9Xy7D+kbF3KTMzRw/3fFWj+7+lhk0jdFvzG8wK/7IFViinsdN6asqjSzSk/UuKO5akAY+1L7BdtRqhmrZoiFrcXduwvuq1IUpLydSIrvPyf0pSERRY0V9j5/TVlEELNaT584o7ekoDJnQtsF21iEqa9tEotejcoMBtbXreptmfjlVI5SAzQi4ygcH+GvtyH015+B0NaTlVcX8masDTnQtsV+36cE37cIRadK5nWN/r0Tvl4eWh4e1maFi76fLx9db9I9qZFf5ly9/3g9/UkBYvuPb9M10KbFctIlzTVoxUi3vqF7itTc9Gmv1Jydv3krWP/UtyOs37cTPTCqFt27YpNdX1jvmTTz7RCy+8oJUrV5r18AXUb11LB3f9rpgj8ZKkz97+Sq17Ni70Nh6eHvL1KyPvMt7yLuMlL28v5WTlKi/Xrj6R43R4z5+SpMrVQ5WalG5iZv9c/cbX6cCvJxRzLEmStPajH9T6Ly/2knTPfY20cc1P+nrTL4b1ETdW0Zfr9sjhcCovz67vth9U8zY3mRJ7UajfPEIH9x5XzNFESdLaD75Vq7+84ElSpz5NtOnjH7Tt872G9TfVu0YOh1PTFw/Ra6tHqffwNvLwsJkSe1Go3/JGHfz5qGJ+T5AkrV30tVrd27DAdp0G3K5Ny6K1bc2PhvXB4YFq0r6unuvzqinxFqX6LSN1cPef53JfvF2tut1aYLtO/Vto0/JvtW3NT4b1//v2sJbN3SCn0ymHw6nDvxxXWNUKpsReFAru+20X3vf9W2rTh99o2+pdhvX5+/7B10yJt6hZ+djHOaYMjU2dOlX79u1TVFSU5syZo71796pNmzbatGmT9u3bpwkTJpgRhkHoVcFKOJGUv5xw4rTKBfrJr7xv/vDY322zael2teh6q5bsf0menp7a9dX/9O363ZIke55dQaEBmv/1RAVU9Ne0Aa+bm9w/FBoeaBjWSYhPVTl/X/mVK2MYHnp15jpJ0i0Naxjuv/9/x9WmQx398vOf8vbxUvPWNykvz25O8EUgpFKgEuKS85dPxaWoXPmC+S+YvFqSdEvj6w339/T00E87Duntmevk4+ut5xf2V0Z6lj5ZtMOcBC5TSJUKSjhxOn/5VEyyygWUlZ+/r2GIYMF419DvLS1qGu6fdDJFUwYtNCfYIhZSJUgJMeflHnuR3Cd8JEm6pZmx07nr6/35/w+rWkFdB92heU8uK+aoi06h83/m7L5vfqF9/6Y5wRYDKx/7l3QFdGrMYkpHaMeOHVq0aJFCQ0O1ZcsWLViwQL1799arr76qHTvc82Jhu8g7drvdUaht+jzVRSmn0vTA9aP14E3jVD6onO4dcVf+NskJqXrwxnEa226qxr42UFWvCy/aBIrQxboX5/8t/s7CqI1yOqXX3h+qibPv165vDysvt+QUQhfN31G4/Nev+F6vT12j3Fy7zqRladW729W0ba1L3/EKcbn5l2Qetss79v/f9bWradbHo7Tmv1/ruy9/ufQdrhAeHhd+Cfin+ZdUVj72cY4phZCvr68SE13DDhUrVlRGRoYkKTMzU15e7pmvnXAsUcHh58Z0Q6pUUNrpdGVn5BRqm2ad62vDku3Ky7UrIzVTX3ywU3VbRMovoKyadjo3jv7b7j/1+95jql7rKnMS+xfi41IUHOKfvxwSWl5pKZnKLuSET79yZfT2vE165P7X9PTw9+R0OhVzPOnSd7xCxMcmKzg0IH85JDxAackZys4sXP6tu9RT9ZqV8pdtNpWojlj8idMKDj8v/8pBSjt9xvBcKK3iY04rOCwwfzmkUqDSks8oO7Pwube8p75e/GCY3p22Rh/O31QcYRab+BNJxvz/f9//g/xLMisf+zjHlEJoxIgR6tGjh2bMmKEaNWqob9++evHFF3XfffdpwIABZoRQwI+bf1FkwxqqUiNMktRx4B2K/uznQm/z2+4/dXs311iyp5enGne4Rfu/PyyH3aExrw7QTbe5hk+uiayiq26orAM/HDEnsX/hx28OK/Lmq1SlWrAkqWP3WxW9df8l7nVOp+63qt/QVpKkoOByurtrA321fu8l7nXl2LX9kCLrVlOVaypKkjr0uk3RX/5a6PtXjwhX35Ht5OFhk08ZL3Xu01Rfr9tTXOEWuV1bf1Vkg2tV5dpQSVKHfi0UvaHkxH85dm3dr8j615zLvW9zRW8o/LHbvOMtGvpCdz3T+zVt+eTHS9/hCrNryz5FNqh+3r5vbpl9L1n72L8kC02WNqUd07p1a0VEROiLL77Q0aNHdcstt6hcuXKaPn266tSpY0YIBaScStPLw97RhMXD5eXjqdjfEzRr6FuKqFddo+f11/AWky66jSS98fQHGjarj978fqocdod+3rpPy+d8LnueXS/0fkVDpz8gTy9P5ebkacbgN3TqvHH4K03K6TN66YVP9eyM++Tl7anY46c1a+IqRdxYRWMm3KNhff5+jtOy/27TEy/cqzc+HCabpPcWbtHBX2PMCb4IpCSdUdTTH+mZeQ+68v8zUbOfXK6Im6tq1JTuGtF13t/ef+n8LzXsuS5asGa0PL08tW39Xq1f8b1J0V++lFPpihr9np55a4i8vL0UezRBsx9dpIi6V2vUS300ou00d4dYbFIS0xU17n0988ZA174/ekqzRy9RRJ1qGjXrAY24a+bf3r//U51ks9k0atYD+et+/f53vTZhRXGHXiRSEtMVNXqJnnlzsLx8vBT7R4Jmj1zs2vez+2hEu9K77yVrH/s4x+Z0XgHl2D/UPnCgu0NwG2fE1e4Owa080i78+R6WkZJ66W1KKzcNo18x7CVnuLVYlLyXqiL1eZy5V+bdXXm4aY/1eax7r7qz7OcIAQAAWPwtFgAAKMBCHTg6QgAAwLLoCAEAACM68MyskwAABrtJREFUQgAAAKUfHSEAAGDkoCMEAABQ6tERAgAABk6ndb5vjY4QAACwLDpCAADAiDlCAAAApR8dIQAAYMTnCAEAAJR+FEIAAMCyGBoDAABGDi6fBwAAKPXoCAEAACMmSwMAAJR+dIQAAICBkzlCAAAApR8dIQAAYMQcIQAAgNKPjhAAADDiS1cBAABKPzpCAADAyMlVYwAAAKUeHSEAAGDgZI4QAABA6UdHCAAAGDFHCAAAoPSjEAIAAJbF0BgAADBgsjQAAIAF0BECAABGFposbXM6LfQVswAAAOdhaAwAAFgWhRAAALAsCiEAAGBZFEIAAMCyKIQAAIBlUQgBAADLohACAACWRSEEAAAsi0IIAABYFoXQP7BmzRp16NBB7dq109KlS90djunS09PVqVMnHT9+3N2hmG7+/Pnq2LGjOnbsqJkzZ7o7HNPNnTtXHTp0UMeOHfXuu++6Oxy3mTFjhp566il3h2G6fv36qWPHjurSpYu6dOmi3bt3uzskU23evFn33nuv2rdvrylTprg7HBQxvmuskE6ePKmoqCh9/PHH8vHxUa9evXTbbbfp+uuvd3dopti9e7cmTJigP/74w92hmG7nzp3avn27Vq1aJZvNpsGDB2vTpk1q166du0MzxXfffadvvvlGq1evVl5enjp06KCWLVuqRo0a7g7NVNHR0Vq1apXuuOMOd4diKqfTqSNHjmjLli3y8rLeS8axY8c0ceJErVixQhUrVtRDDz2krVu3qmXLlu4ODUWEjlAh7dy5U40bN1ZQUJD8/Px01113af369e4OyzTLly/XxIkTFRYW5u5QTBcaGqqnnnpKPj4+8vb21nXXXaeYmBh3h2WaRo0aafHixfLy8lJiYqLsdrv8/PzcHZapkpOTFRUVpaFDh7o7FNMdOXJENptNQ4YM0T333KMlS5a4OyRTbdq0SR06dFClSpXk7e2tqKgo1a1b191hoQhZr7z/l+Lj4xUaGpq/HBYWpj179rgxInNNnTrV3SG4TURERP7///jjD61bt07Lli1zY0Tm8/b21rx58/TOO++offv2Cg8Pd3dIpnruuec0ZswYxcbGujsU06WmpqpJkyaaNGmSsrKy1K9fP1177bVq1qyZu0MzxdGjR+Xt7a1BgwYpISFBrVq10ujRo90dFooQHaFCcjqdBdbZbDY3RAJ3OXTokAYOHKgnn3xS1atXd3c4phs5cqSio6MVGxur5cuXuzsc06xYsUKVK1dWkyZN3B2KW9SrV08zZ86Un5+fgoOD1aNHD23dutXdYZnGbrcrOjpas2bN0vLly7V3716tWrXK3WGhCFEIFVJ4eLhOnTqVvxwfH2/JYSKr+vHHH9W/f3+NGzdO3bp1c3c4pjp8+LD27dsnSSpbtqzuvPNOHThwwM1RmWfdunXasWOHunTponnz5mnz5s168cUX3R2WaX744QdFR0fnLzudTkvNFQoJCVGTJk0UHBwsX19ftWnTxlKjAVZAIVRITZs2VXR0tJKSkpSZmamNGzfq9ttvd3dYMEFsbKyGDx+u2bNnq2PHju4Ox3THjx/XhAkTlJOTo5ycHH355Zdq0KCBu8Myzbvvvqu1a9fq008/1ciRI9W6dWuNHz/e3WGZJi0tTTNnzlR2drbS09O1atUqy1woIEmtWrXS9u3blZqaKrvdrm3btqlWrVruDgtFyDpl/WUKDw/XmDFj1K9fP+Xm5qpHjx6qU6eOu8OCCd5++21lZ2dr+vTp+et69eqlBx54wI1Rmadly5bavXu3unbtKk9PT915552WLAitqlWrVvn73+FwqHfv3qpXr567wzJN3bp1NXjwYPXu3Vu5ublq1qyZunfv7u6wUIRszgtNfgEAALAAhsYAAIBlUQgBAADLohACAACWRSEEAAAsi0IIAABYFoUQAACwLAohAABgWRRCAArl7rvv1u23365Dhw65OxQAKDIUQgAKZe3atapevbo2bNjg7lAAoMhQCAEoFE9PTzVo0MBSX7gKoPTju8YAFEpWVpY+++wz8a08AEoTOkIACiUqKkrh4eE6duyYzpw54+5wAKBIUAgBuKSffvpJ69ev1yuvvKLy5cvr4MGD7g4JAIoEhRCAv5Wdna2nn35azz//vIKCghQZGck8IQClBoUQgL81d+5c1atXT3fccYckKTIyUvv373dvUABQRCiEAFzUnj17tH79eo0fPz5/3Y033khHCECpYXNyCQgAALAoOkIAAMCyKIQAAIBlUQgBAADLohACAACWRSEEAAAsi0IIAABYFoUQAACwLAohAABgWf8HACBPxW0RDPcAAAAASUVORK5CYII=\n",
+      "text/plain": [
+       "<Figure size 720x720 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "# optional\n",
     "# visual representation of grid search\n",
@@ -2474,9 +3299,7 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "pip3 install tensorflow"
@@ -2492,9 +3315,7 @@
   {
    "cell_type": "code",
    "execution_count": 14,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "conda install tensorflow"
@@ -2509,11 +3330,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "inputs = (n_inputs, pixel_width, pixel_height) = (1797, 8, 8)\n",
+      "labels = (n_inputs) = (1797,)\n",
+      "X = (n_inputs, n_features) = (1797, 64)\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 864x864 with 5 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "# import necessary packages\n",
     "import numpy as np\n",
@@ -2561,11 +3402,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Using TensorFlow backend.\n"
+     ]
+    }
+   ],
    "source": [
     "from keras.utils import to_categorical\n",
     "from sklearn.model_selection import train_test_split\n",
@@ -2593,10 +3440,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 3,
+   "metadata": {},
    "outputs": [],
    "source": [
     "import tensorflow as tf\n",
@@ -2741,10 +3586,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 4,
+   "metadata": {},
    "outputs": [],
    "source": [
     "epochs = 100\n",
@@ -2758,11 +3601,212 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate =  1e-05\n",
+      "Lambda =  1e-05\n",
+      "Test accuracy: 0.092\n",
+      "\n",
+      "Learning rate =  1e-05\n",
+      "Lambda =  0.0001\n",
+      "Test accuracy: 0.114\n",
+      "\n",
+      "Learning rate =  1e-05\n",
+      "Lambda =  0.001\n",
+      "Test accuracy: 0.067\n",
+      "\n",
+      "Learning rate =  1e-05\n",
+      "Lambda =  0.01\n",
+      "Test accuracy: 0.125\n",
+      "\n",
+      "Learning rate =  1e-05\n",
+      "Lambda =  0.1\n",
+      "Test accuracy: 0.114\n",
+      "\n",
+      "Learning rate =  1e-05\n",
+      "Lambda =  1.0\n",
+      "Test accuracy: 0.092\n",
+      "\n",
+      "Learning rate =  1e-05\n",
+      "Lambda =  10.0\n",
+      "Test accuracy: 0.125\n",
+      "\n",
+      "Learning rate =  0.0001\n",
+      "Lambda =  1e-05\n",
+      "Test accuracy: 0.106\n",
+      "\n",
+      "Learning rate =  0.0001\n",
+      "Lambda =  0.0001\n",
+      "Test accuracy: 0.058\n",
+      "\n",
+      "Learning rate =  0.0001\n",
+      "Lambda =  0.001\n",
+      "Test accuracy: 0.117\n",
+      "\n",
+      "Learning rate =  0.0001\n",
+      "Lambda =  0.01\n",
+      "Test accuracy: 0.075\n",
+      "\n",
+      "Learning rate =  0.0001\n",
+      "Lambda =  0.1\n",
+      "Test accuracy: 0.089\n",
+      "\n",
+      "Learning rate =  0.0001\n",
+      "Lambda =  1.0\n",
+      "Test accuracy: 0.111\n",
+      "\n",
+      "Learning rate =  0.0001\n",
+      "Lambda =  10.0\n",
+      "Test accuracy: 0.114\n",
+      "\n",
+      "Learning rate =  0.001\n",
+      "Lambda =  1e-05\n",
+      "Test accuracy: 0.217\n",
+      "\n",
+      "Learning rate =  0.001\n",
+      "Lambda =  0.0001\n",
+      "Test accuracy: 0.239\n",
+      "\n",
+      "Learning rate =  0.001\n",
+      "Lambda =  0.001\n",
+      "Test accuracy: 0.175\n",
+      "\n",
+      "Learning rate =  0.001\n",
+      "Lambda =  0.01\n",
+      "Test accuracy: 0.178\n",
+      "\n",
+      "Learning rate =  0.001\n",
+      "Lambda =  0.1\n",
+      "Test accuracy: 0.206\n",
+      "\n",
+      "Learning rate =  0.001\n",
+      "Lambda =  1.0\n",
+      "Test accuracy: 0.194\n",
+      "\n",
+      "Learning rate =  0.001\n",
+      "Lambda =  10.0\n",
+      "Test accuracy: 0.089\n",
+      "\n",
+      "Learning rate =  0.01\n",
+      "Lambda =  1e-05\n",
+      "Test accuracy: 0.828\n",
+      "\n",
+      "Learning rate =  0.01\n",
+      "Lambda =  0.0001\n",
+      "Test accuracy: 0.733\n",
+      "\n",
+      "Learning rate =  0.01\n",
+      "Lambda =  0.001\n",
+      "Test accuracy: 0.742\n",
+      "\n",
+      "Learning rate =  0.01\n",
+      "Lambda =  0.01\n",
+      "Test accuracy: 0.769\n",
+      "\n",
+      "Learning rate =  0.01\n",
+      "Lambda =  0.1\n",
+      "Test accuracy: 0.272\n",
+      "\n",
+      "Learning rate =  0.01\n",
+      "Lambda =  1.0\n",
+      "Test accuracy: 0.089\n",
+      "\n",
+      "Learning rate =  0.01\n",
+      "Lambda =  10.0\n",
+      "Test accuracy: 0.078\n",
+      "\n",
+      "Learning rate =  0.1\n",
+      "Lambda =  1e-05\n",
+      "Test accuracy: 0.983\n",
+      "\n",
+      "Learning rate =  0.1\n",
+      "Lambda =  0.0001\n",
+      "Test accuracy: 0.978\n",
+      "\n",
+      "Learning rate =  0.1\n",
+      "Lambda =  0.001\n",
+      "Test accuracy: 0.967\n",
+      "\n",
+      "Learning rate =  0.1\n",
+      "Lambda =  0.01\n",
+      "Test accuracy: 0.964\n",
+      "\n",
+      "Learning rate =  0.1\n",
+      "Lambda =  0.1\n",
+      "Test accuracy: 0.089\n",
+      "\n",
+      "Learning rate =  0.1\n",
+      "Lambda =  1.0\n",
+      "Test accuracy: 0.092\n",
+      "\n",
+      "Learning rate =  0.1\n",
+      "Lambda =  10.0\n",
+      "Test accuracy: 0.092\n",
+      "\n",
+      "Learning rate =  1.0\n",
+      "Lambda =  1e-05\n",
+      "Test accuracy: 0.975\n",
+      "\n",
+      "Learning rate =  1.0\n",
+      "Lambda =  0.0001\n",
+      "Test accuracy: 0.978\n",
+      "\n",
+      "Learning rate =  1.0\n",
+      "Lambda =  0.001\n",
+      "Test accuracy: 0.967\n",
+      "\n",
+      "Learning rate =  1.0\n",
+      "Lambda =  0.01\n",
+      "Test accuracy: 0.419\n",
+      "\n",
+      "Learning rate =  1.0\n",
+      "Lambda =  0.1\n",
+      "Test accuracy: 0.106\n",
+      "\n",
+      "Learning rate =  1.0\n",
+      "Lambda =  1.0\n",
+      "Test accuracy: 0.106\n",
+      "\n",
+      "Learning rate =  1.0\n",
+      "Lambda =  10.0\n",
+      "Test accuracy: 0.078\n",
+      "\n",
+      "Learning rate =  10.0\n",
+      "Lambda =  1e-05\n",
+      "Test accuracy: 0.092\n",
+      "\n",
+      "Learning rate =  10.0\n",
+      "Lambda =  0.0001\n",
+      "Test accuracy: 0.117\n",
+      "\n",
+      "Learning rate =  10.0\n",
+      "Lambda =  0.001\n",
+      "Test accuracy: 0.078\n",
+      "\n",
+      "Learning rate =  10.0\n",
+      "Lambda =  0.01\n",
+      "Test accuracy: 0.172\n",
+      "\n",
+      "Learning rate =  10.0\n",
+      "Lambda =  0.1\n",
+      "Test accuracy: 0.106\n",
+      "\n",
+      "Learning rate =  10.0\n",
+      "Lambda =  1.0\n",
+      "Test accuracy: 0.078\n",
+      "\n",
+      "Learning rate =  10.0\n",
+      "Lambda =  10.0\n",
+      "Test accuracy: 0.078\n",
+      "\n"
+     ]
+    }
+   ],
    "source": [
     "DNN_tf = np.zeros((len(eta_vals), len(lmbd_vals)), dtype=object)\n",
     "        \n",
@@ -2783,11 +3827,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 720x720 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 720x720 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "# optional\n",
     "# visual representation of grid search\n",
@@ -2824,10 +3887,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 7,
+   "metadata": {},
    "outputs": [],
    "source": [
     "# optional\n",
@@ -2851,9 +3912,7 @@
   {
    "cell_type": "code",
    "execution_count": 22,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "conda install keras"
@@ -2869,9 +3928,7 @@
   {
    "cell_type": "code",
    "execution_count": 23,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "pip3 install keras"
@@ -2886,10 +3943,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 8,
+   "metadata": {},
    "outputs": [],
    "source": [
     "from keras.models import Sequential\n",
@@ -2911,11 +3966,261 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "360/360 [==============================] - 0s 1ms/step\n",
+      "Learning rate =  1e-05\n",
+      "Lambda =  1e-05\n",
+      "Test accuracy: 0.086\n",
+      "\n",
+      "360/360 [==============================] - 0s 1ms/step\n",
+      "Learning rate =  1e-05\n",
+      "Lambda =  0.0001\n",
+      "Test accuracy: 0.078\n",
+      "\n",
+      "360/360 [==============================] - 0s 1ms/step\n",
+      "Learning rate =  1e-05\n",
+      "Lambda =  0.001\n",
+      "Test accuracy: 0.044\n",
+      "\n",
+      "360/360 [==============================] - 0s 1ms/step\n",
+      "Learning rate =  1e-05\n",
+      "Lambda =  0.01\n",
+      "Test accuracy: 0.117\n",
+      "\n",
+      "360/360 [==============================] - 0s 1ms/step\n",
+      "Learning rate =  1e-05\n",
+      "Lambda =  0.1\n",
+      "Test accuracy: 0.056\n",
+      "\n",
+      "360/360 [==============================] - 0s 1ms/step\n",
+      "Learning rate =  1e-05\n",
+      "Lambda =  1.0\n",
+      "Test accuracy: 0.128\n",
+      "\n",
+      "360/360 [==============================] - 0s 1ms/step\n",
+      "Learning rate =  1e-05\n",
+      "Lambda =  10.0\n",
+      "Test accuracy: 0.128\n",
+      "\n",
+      "360/360 [==============================] - 0s 1ms/step\n",
+      "Learning rate =  0.0001\n",
+      "Lambda =  1e-05\n",
+      "Test accuracy: 0.092\n",
+      "\n",
+      "360/360 [==============================] - 0s 1ms/step\n",
+      "Learning rate =  0.0001\n",
+      "Lambda =  0.0001\n",
+      "Test accuracy: 0.086\n",
+      "\n",
+      "360/360 [==============================] - 0s 1ms/step\n",
+      "Learning rate =  0.0001\n",
+      "Lambda =  0.001\n",
+      "Test accuracy: 0.078\n",
+      "\n",
+      "360/360 [==============================] - 1s 1ms/step\n",
+      "Learning rate =  0.0001\n",
+      "Lambda =  0.01\n",
+      "Test accuracy: 0.092\n",
+      "\n",
+      "360/360 [==============================] - 1s 1ms/step\n",
+      "Learning rate =  0.0001\n",
+      "Lambda =  0.1\n",
+      "Test accuracy: 0.156\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.0001\n",
+      "Lambda =  1.0\n",
+      "Test accuracy: 0.039\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.0001\n",
+      "Lambda =  10.0\n",
+      "Test accuracy: 0.117\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.001\n",
+      "Lambda =  1e-05\n",
+      "Test accuracy: 0.364\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.001\n",
+      "Lambda =  0.0001\n",
+      "Test accuracy: 0.353\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.001\n",
+      "Lambda =  0.001\n",
+      "Test accuracy: 0.331\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.001\n",
+      "Lambda =  0.01\n",
+      "Test accuracy: 0.247\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.001\n",
+      "Lambda =  0.1\n",
+      "Test accuracy: 0.344\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.001\n",
+      "Lambda =  1.0\n",
+      "Test accuracy: 0.114\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.001\n",
+      "Lambda =  10.0\n",
+      "Test accuracy: 0.106\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.01\n",
+      "Lambda =  1e-05\n",
+      "Test accuracy: 0.875\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.01\n",
+      "Lambda =  0.0001\n",
+      "Test accuracy: 0.889\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.01\n",
+      "Lambda =  0.001\n",
+      "Test accuracy: 0.861\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.01\n",
+      "Lambda =  0.01\n",
+      "Test accuracy: 0.858\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.01\n",
+      "Lambda =  0.1\n",
+      "Test accuracy: 0.514\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.01\n",
+      "Lambda =  1.0\n",
+      "Test accuracy: 0.089\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.01\n",
+      "Lambda =  10.0\n",
+      "Test accuracy: 0.089\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.1\n",
+      "Lambda =  1e-05\n",
+      "Test accuracy: 0.978\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.1\n",
+      "Lambda =  0.0001\n",
+      "Test accuracy: 0.983\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.1\n",
+      "Lambda =  0.001\n",
+      "Test accuracy: 0.983\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.1\n",
+      "Lambda =  0.01\n",
+      "Test accuracy: 0.964\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.1\n",
+      "Lambda =  0.1\n",
+      "Test accuracy: 0.747\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.1\n",
+      "Lambda =  1.0\n",
+      "Test accuracy: 0.106\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  0.1\n",
+      "Lambda =  10.0\n",
+      "Test accuracy: 0.156\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  1.0\n",
+      "Lambda =  1e-05\n",
+      "Test accuracy: 0.983\n",
+      "\n",
+      "360/360 [==============================] - 1s 2ms/step\n",
+      "Learning rate =  1.0\n",
+      "Lambda =  0.0001\n",
+      "Test accuracy: 0.983\n",
+      "\n",
+      "360/360 [==============================] - 1s 3ms/step\n",
+      "Learning rate =  1.0\n",
+      "Lambda =  0.001\n",
+      "Test accuracy: 0.886\n",
+      "\n",
+      "360/360 [==============================] - 1s 3ms/step\n",
+      "Learning rate =  1.0\n",
+      "Lambda =  0.01\n",
+      "Test accuracy: 0.383\n",
+      "\n",
+      "360/360 [==============================] - 1s 3ms/step\n",
+      "Learning rate =  1.0\n",
+      "Lambda =  0.1\n",
+      "Test accuracy: 0.089\n",
+      "\n",
+      "360/360 [==============================] - 1s 3ms/step\n",
+      "Learning rate =  1.0\n",
+      "Lambda =  1.0\n",
+      "Test accuracy: 0.114\n",
+      "\n",
+      "360/360 [==============================] - 1s 3ms/step\n",
+      "Learning rate =  1.0\n",
+      "Lambda =  10.0\n",
+      "Test accuracy: 0.078\n",
+      "\n",
+      "360/360 [==============================] - 1s 3ms/step\n",
+      "Learning rate =  10.0\n",
+      "Lambda =  1e-05\n",
+      "Test accuracy: 0.106\n",
+      "\n",
+      "360/360 [==============================] - 1s 3ms/step\n",
+      "Learning rate =  10.0\n",
+      "Lambda =  0.0001\n",
+      "Test accuracy: 0.117\n",
+      "\n",
+      "360/360 [==============================] - 1s 3ms/step\n",
+      "Learning rate =  10.0\n",
+      "Lambda =  0.001\n",
+      "Test accuracy: 0.106\n",
+      "\n",
+      "360/360 [==============================] - 1s 3ms/step\n",
+      "Learning rate =  10.0\n",
+      "Lambda =  0.01\n",
+      "Test accuracy: 0.125\n",
+      "\n",
+      "360/360 [==============================] - 1s 3ms/step\n",
+      "Learning rate =  10.0\n",
+      "Lambda =  0.1\n",
+      "Test accuracy: 0.089\n",
+      "\n",
+      "360/360 [==============================] - 1s 3ms/step\n",
+      "Learning rate =  10.0\n",
+      "Lambda =  1.0\n",
+      "Test accuracy: 0.078\n",
+      "\n",
+      "360/360 [==============================] - 1s 3ms/step\n",
+      "Learning rate =  10.0\n",
+      "Lambda =  10.0\n",
+      "Test accuracy: 0.078\n",
+      "\n"
+     ]
+    }
+   ],
    "source": [
     "DNN_keras = np.zeros((len(eta_vals), len(lmbd_vals)), dtype=object)\n",
     "        \n",
@@ -2936,11 +4241,134 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1437/1437 [==============================] - 0s 64us/step\n",
+      "360/360 [==============================] - 0s 63us/step\n",
+      "1437/1437 [==============================] - 0s 60us/step\n",
+      "360/360 [==============================] - 0s 90us/step\n",
+      "1437/1437 [==============================] - 0s 61us/step\n",
+      "360/360 [==============================] - 0s 82us/step\n",
+      "1437/1437 [==============================] - 0s 58us/step\n",
+      "360/360 [==============================] - 0s 60us/step\n",
+      "1437/1437 [==============================] - 0s 64us/step\n",
+      "360/360 [==============================] - 0s 64us/step\n",
+      "1437/1437 [==============================] - 0s 63us/step\n",
+      "360/360 [==============================] - 0s 65us/step\n",
+      "1437/1437 [==============================] - 0s 62us/step\n",
+      "360/360 [==============================] - 0s 70us/step\n",
+      "1437/1437 [==============================] - 0s 57us/step\n",
+      "360/360 [==============================] - 0s 83us/step\n",
+      "1437/1437 [==============================] - 0s 61us/step\n",
+      "360/360 [==============================] - 0s 73us/step\n",
+      "1437/1437 [==============================] - 0s 68us/step\n",
+      "360/360 [==============================] - 0s 69us/step\n",
+      "1437/1437 [==============================] - 0s 71us/step\n",
+      "360/360 [==============================] - 0s 65us/step\n",
+      "1437/1437 [==============================] - 0s 83us/step\n",
+      "360/360 [==============================] - 0s 70us/step\n",
+      "1437/1437 [==============================] - 0s 80us/step\n",
+      "360/360 [==============================] - 0s 75us/step\n",
+      "1437/1437 [==============================] - 0s 66us/step\n",
+      "360/360 [==============================] - 0s 75us/step\n",
+      "1437/1437 [==============================] - 0s 72us/step\n",
+      "360/360 [==============================] - 0s 78us/step\n",
+      "1437/1437 [==============================] - 0s 76us/step\n",
+      "360/360 [==============================] - 0s 78us/step\n",
+      "1437/1437 [==============================] - 0s 71us/step\n",
+      "360/360 [==============================] - 0s 92us/step\n",
+      "1437/1437 [==============================] - 0s 67us/step\n",
+      "360/360 [==============================] - 0s 66us/step\n",
+      "1437/1437 [==============================] - 0s 78us/step\n",
+      "360/360 [==============================] - 0s 79us/step\n",
+      "1437/1437 [==============================] - 0s 80us/step\n",
+      "360/360 [==============================] - 0s 79us/step\n",
+      "1437/1437 [==============================] - 0s 70us/step\n",
+      "360/360 [==============================] - 0s 83us/step\n",
+      "1437/1437 [==============================] - 0s 76us/step\n",
+      "360/360 [==============================] - 0s 71us/step\n",
+      "1437/1437 [==============================] - 0s 68us/step\n",
+      "360/360 [==============================] - 0s 70us/step\n",
+      "1437/1437 [==============================] - 0s 68us/step\n",
+      "360/360 [==============================] - 0s 64us/step\n",
+      "1437/1437 [==============================] - 0s 58us/step\n",
+      "360/360 [==============================] - 0s 65us/step\n",
+      "1437/1437 [==============================] - 0s 71us/step\n",
+      "360/360 [==============================] - 0s 65us/step\n",
+      "1437/1437 [==============================] - 0s 70us/step\n",
+      "360/360 [==============================] - 0s 66us/step\n",
+      "1437/1437 [==============================] - 0s 70us/step\n",
+      "360/360 [==============================] - 0s 74us/step\n",
+      "1437/1437 [==============================] - 0s 64us/step\n",
+      "360/360 [==============================] - 0s 66us/step\n",
+      "1437/1437 [==============================] - 0s 74us/step\n",
+      "360/360 [==============================] - 0s 65us/step\n",
+      "1437/1437 [==============================] - 0s 65us/step\n",
+      "360/360 [==============================] - 0s 69us/step\n",
+      "1437/1437 [==============================] - 0s 62us/step\n",
+      "360/360 [==============================] - 0s 72us/step\n",
+      "1437/1437 [==============================] - 0s 64us/step\n",
+      "360/360 [==============================] - 0s 83us/step\n",
+      "1437/1437 [==============================] - 0s 78us/step\n",
+      "360/360 [==============================] - 0s 74us/step\n",
+      "1437/1437 [==============================] - 0s 77us/step\n",
+      "360/360 [==============================] - 0s 73us/step\n",
+      "1437/1437 [==============================] - 0s 66us/step\n",
+      "360/360 [==============================] - 0s 82us/step\n",
+      "1437/1437 [==============================] - 0s 60us/step\n",
+      "360/360 [==============================] - 0s 71us/step\n",
+      "1437/1437 [==============================] - 0s 68us/step\n",
+      "360/360 [==============================] - 0s 79us/step\n",
+      "1437/1437 [==============================] - 0s 64us/step\n",
+      "360/360 [==============================] - 0s 73us/step\n",
+      "1437/1437 [==============================] - 0s 67us/step\n",
+      "360/360 [==============================] - 0s 67us/step\n",
+      "1437/1437 [==============================] - 0s 66us/step\n",
+      "360/360 [==============================] - 0s 63us/step\n",
+      "1437/1437 [==============================] - 0s 68us/step\n",
+      "360/360 [==============================] - 0s 72us/step\n",
+      "1437/1437 [==============================] - 0s 64us/step\n",
+      "360/360 [==============================] - 0s 85us/step\n",
+      "1437/1437 [==============================] - 0s 61us/step\n",
+      "360/360 [==============================] - 0s 91us/step\n",
+      "1437/1437 [==============================] - 0s 66us/step\n",
+      "360/360 [==============================] - 0s 66us/step\n",
+      "1437/1437 [==============================] - 0s 66us/step\n",
+      "360/360 [==============================] - 0s 70us/step\n",
+      "1437/1437 [==============================] - 0s 65us/step\n",
+      "360/360 [==============================] - 0s 80us/step\n",
+      "1437/1437 [==============================] - 0s 67us/step\n",
+      "360/360 [==============================] - 0s 75us/step\n",
+      "1437/1437 [==============================] - 0s 72us/step\n",
+      "360/360 [==============================] - 0s 66us/step\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 720x720 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 720x720 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "# optional\n",
     "# visual representation of grid search\n",
@@ -2974,9 +4402,34 @@
     "ax.set_xlabel(\"$\\lambda$\")\n",
     "plt.show()"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
- "metadata": {},
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.6"
+  }
+ },
  "nbformat": 4,
  "nbformat_minor": 2
 }
diff --git a/doc/src/Projects/2018/Project2/Project2.do.txt b/doc/src/Projects/2018/Project2/Project2.do.txt
index f06ec4c8f..60432fee0 100644
--- a/doc/src/Projects/2018/Project2/Project2.do.txt
+++ b/doc/src/Projects/2018/Project2/Project2.do.txt
@@ -11,7 +11,7 @@ o link to mehta's article
 ===== Classification and Regression, from linear and logistic regression to neural networks  =====
 
 The main aim of this project is to study both classification and
-regression problems, starting with the regression algortihms studied
+regression problems, starting with the regression algorithms studied
 in project 1. We will include logistic regresion for classification
 problems and write our own multilayer perceptron code for studying
 both regression and classification problems.  The codes developed in
@@ -20,19 +20,20 @@ computation of the mean-squared error and the R2 score function can
 also be utilized (and included in logistic regression and the neural
 network codes) in the present analysis.
 
-We will use the Ising model to generate our training data and will
-focus mainly on supervised training. We will follow closely the recent
+We will use the so-called Ising model for  our training data and will
+focus on supervised training. We will follow closely the recent
 article of "Mehta et al, arXiv
 1803.08823":"https://arxiv.org/abs/1803.08823". This article stands
-out as an excellent review on machine learning (ML) algorithms applied
-to typical physics problems. The added benefit is that each figure and
+out as an excellent review on machine learning (ML) algorithms.
+The added benefit is that each figure and
 model presented in "this article is accompanied by its jupyter
 notebook":"https://physics.bu.edu/~pankajm/MLnotebooks.html". This
-means that we can start using these and compare with our own
-results. In case you wish to use their data for the Ising model, their
-data can be downloaded from the same link which lists to the jupyter
-notebooks. See also at the end of the project description for more
-information on how to install various Python packages.
+means that we can start using these and compare with our own results.
+They provide also the data set for the regression and classification
+analysis that we will explore.  In this sense, with their available
+notebooks, it makes life easier since we can compare our own codes
+with their codes.
+
 
 
 
@@ -49,71 +50,258 @@ that is the two-dimensional Ising model, will be studied using
 logistic regression and deep neural networks.  The aim is to develop
 your own logistic regression code for the classification of the phases
 (this is a binary model) and your multilayer perceptron code for the
-classification and regression case.
+classification and regression case. You can compare your own results with those obtained
+using _scikit-learn_ or _tensorflow_ or other Python packages such as _keras_ or other.
 
 
 Feel free to use the notebooks to benchmark your code.  If you wish to
-write your own C++ or Fortran program for say a simple neural network
-model and a logistic regression model, please feel free to do so.  You can then benchmark your results
-against the above jupyter notebooks.
+write your own C++ or Fortran program for say a multilayer neural network
+model and a logistic regression model, please feel free to do so.  
 
 
-=== Part a): Producing the data  ===
+=== Part a): Producing the data for the one-dimensional Ising model ===
 
-You can use the Ising model data from the article of Mehta *et al.*,
-or generate your own data.  If you opt for using your own Ising model
-code, you need to generate $10000$ energy configurations with their
-spin orientations after the system has reached its most likely
-state. These energies and their corresponding spin orientations
-represent then your data.  We will use a fixed lattice of $L\times L =
-40 \times 40$ spins in two dimensions and $L=40$ spins in one
-dimension.  Make sure the calculations have been equilibrated. For the
-two-dimensional system, compute the configurations for three values of
-the temperature, namely $T=0.75$ (ordered phase), $T=2.3$ (near the
-critical point) and $T=4.0$ (disordered phase).  For the
-one-dimensional system it suffices to compute the various
-configurations for one temperature only, say $T=2.0$.  These are the
-data you will use to study different ML algorithms.  We generate our
-data with $J=1$.
 
-=== Part b): Estimating the coupling constant of the one-dimensional Ising model  ===
+
+The model we will employ in our studies is the so-called "Ising
+model":"https://en.wikipedia.org/wiki/Ising_model".  Together with
+models like the "Potts
+model":"https://en.wikipedia.org/wiki/Potts_model" and similar
+so-called lattice models, the Ising model has been widely studied in
+mathematics (in statistics in particular), physics, "life
+science":"https://journals.aps.org/pre/abstract/10.1103/PhysRevE.93.062402",
+chemistry and even in the "social sciences in order to model social
+behavior":"https://www.springer.com/gp/book/9781461420316". It is a
+simple binary value system where the variables of the model (spins often in
+physics) can take two values only, for example $\pm 1$ or $0$ and $1$.
+The system exhibits a phase transition in two or higher dimensions and
+the first person to find the analytical expressions for various
+expectation values was the Norwegian chemist "Lars
+Onsager":"https://en.wikipedia.org/wiki/Lars_Onsager" (Nobel prize in
+chemistry) after a tour de force mathematics exercise.
+
+In our discussions here we will stay with a physicist's approach and
+call the variables for spin. You could replace this with any other
+type of binary variables, ranging from a two political parties to blue
+and red spheres.  In its simplest form we define the energy of the
+system as
+
+!bt
+\begin{equation*}
+  E=-J\sum_{<kl>}^{N}s_ks_l-{\cal B}\sum_k^Ns_k,
+\end{equation*}
+!et
+with  $s_k=\pm 1$, $N$ is the total number of spins,
+$J$ is a coupling constant expressing the strength of the interaction
+between neighboring spins and
+${\cal B}$ is an external magnetic field interacting with the magnetic
+moment set up by the spins.   We will discard the magnetic field part. 
+
+The symbol $<kl>$ indicates that we sum over nearest
+neighbors only.
+Notice that for $J>0$ it is energetically favorable for neighboring spins
+to be aligned. This feature leads to, at low enough temperatures,
+a cooperative phenomenon called spontaneous magnetization. That is,
+through interactions between nearest neighbors, a given magnetic
+moment can influence the alignment of spins  that are separated
+from the given spin by a macroscopic distance. These long range correlations
+between spins are associated with a long-range order in which
+the lattice has a net magnetization in the absence of a magnetic field.
+
+
+
+We start by considering the one-dimensional Ising model with nearest neighbor interactions. This model does not exhibit any phase transition.
+
+Consider the 1D Ising model with nearest-neighbor interactions 
+
+!bt
+\begin{equation*}
+  E[\hat{s}]=-J\sum_{j=1}^{N}s_{j}s_{j+1},
+\end{equation*}
+!et
+on a chain of length $N$ with so-called periodic boundary conditions and $S_j=\pm 1$ Ising spin variables.
+In one dimension, this model has no phase transition at finite temperature.
+
+In the Python code below we generate, with a coupling coefficient set to $J=1$, a large number of spin configurations say $10000$ as shown in the code below.
+It means that our data will be a set of $i=1\ldots n$ points of the form
+$\{(E[\boldsymbol{s}^i],\boldsymbol{s}^i)\}$.
+Our task is to find the value of $J$ from the data set using linear regression.
+
+Here is the Python code you need to generate the training data, see
+also the "notebook of Mehta et
+al":"https://physics.bu.edu/~pankajm/ML-Notebooks/HTML/NB_CVI-linreg_ising.html".
+
+!bc pycod
+import numpy as np
+import scipy.sparse as sp
+np.random.seed(12)
+
+
+import warnings
+#Comment this to turn on warnings
+warnings.filterwarnings('ignore')
+
+### define Ising model aprams
+# system size
+L=40
+
+# create 10000 random Ising states
+states=np.random.choice([-1, 1], size=(10000,L))
+
+def ising_energies(states,L):
+    """
+    This function calculates the energies of the states in the nn Ising Hamiltonian
+    """
+    J=np.zeros((L,L),)
+    for i in range(L):
+        J[i,(i+1)%L]-=1.0
+    # compute energies
+    E = np.einsum('...i,ij,...j->...',states,J,states)
+
+    return E
+# calculate Ising energies
+energies=ising_energies(states,L)
+!ec
+
+We can now recast the problem as a linear regression model using our codes from project 1.
+The way we are going to build our model mimicks the way we could think of finding say the gravitional constant for the graviational force between two planets.
+In the absence of any prior knowledge, one sensible choice is the all-to-all Ising model
+
+!bt
+\[
+E_\mathrm{model}[\boldsymbol{s}^i] = - \sum_{j=1}^N \sum_{k=1}^N J_{j,k}s_{j}^is_{k}^i.
+\]
+!et
+Here $i$ represents a particular spin configuration (one of the possible $n$ configurations we generated with the code above).
+
+This model is uniquely defined by the non-local coupling strengths $J_{jk}$ which we want to learn.
+The model is linear in ${\mathbf J}$ which makes it possible to use linear regression.
+
+To apply linear regression, we recast this model in the form
+!bt
+\[
+E_\mathrm{model}^i \equiv \mathbf{X}^i \cdot \mathbf{J},
+\]
+!ec
+
+where the vectors $\mathbf{X}^i$ represent all two-body interactions
+$\{s_{j}^is_{k}^i \}_{j,k=1}^N$, and the index $i$ runs over the
+samples in the data set.  To make the analogy complete, we can also
+represent the dot product by a single index $p = \{j,k\}$,
+i.e. $\mathbf{X}^i \cdot \mathbf{J}=X^i_pJ_p$.  Note that the
+regression model does not include the minus sign, so we expect to
+learn negative $J$'s.
+
+With these preliminaries, we are now ready to  reutilize our codes from project 1. 
+
+
+=== Part b): Estimating the coupling constant of the one-dimensional Ising model using linear regression ===
 
 We start with the one-dimensional Ising model and use the data we have
-generated with $J=1$. Use linear regression, Lasso and Ridge
-regression as described section 6 and in Notebook 4 of "Mehta *et
-al.*":"https://physics.bu.edu/~pankajm/ML-Notebooks/HTML/NB_CVI-linreg_ising.html". Discuss
-the methods and how they perform in computing the coupling constant
-$J$. Give a critical analysis and discuss how to evaluate the *cost
-function*. You should feel free to write your own code, see also the
-lecture notes of
-"FYS-STK4155":"https://compphysics.github.io/MachineLearning/doc/web/course.html",
-in particular te material on least square methods.  You can use
-scikit-learn to perform these analyses. See below for instruction on
-how to install scikit-learn.
+generated with $J=1$ in the previous point. Use linear regression,
+Lasso and Ridge regression as done in project 1. You can compare your
+results with those of "Mehta
+et al.":"https://physics.bu.edu/~pankajm/ML-Notebooks/HTML/NB_CVI-linreg_ising.html".
+Make sure it is the 1D data which is used.
+
+Discuss the methods and how they perform in computing the coupling
+constant $J$ and include a bias-variance analysis using either
+cross-validation or bootstrap. Discuss also the mean squared error and
+the $R2$ score as measures to assess your model.
+
+Give a critical analysis of your results.
+
 
 === Part c): Determine the phase of the two-dimensional Ising model  ===
 
 We switch now to binary classification methods and use logistic
-regression to define the phases of the Ising model.  Use described
-section 7 and in Notebook 6 of "Mehta *et
-al.*":"https://physics.bu.edu/~pankajm/ML-Notebooks/HTML/NB_CVII-logreg_ising.html". Discuss
-the methods and how they perform. Give a critical analysis and discuss
-how to evaluate the *cost function*. You should feel free to write
-your own code. 
+regression to define the phases of the Ising model. This means that we switch to the two-dimensional Ising model
+and use the data sets generated by "Mehta et al":"https://physics.bu.edu/~pankajm/ML-Review-Datasets/isingMC/"
+These energies and their corresponding spin orientation configurations 
+represent then your data.  We will use a fixed lattice of $L\times L =
+40 \times 40$ spins in two dimensions. The link above contains data for several temperatures.
+The theoretical critical temperature for a phase transition is $T_C\approx 2.269$ in units of energy.
+However, for a finite lattice the results representing the critical temperature are slightly higher ($T_C \approx 2.3$). 
+
+Our goal here, using logistic regression, is to train our model to
+predict the phase of a sample given the spin configuration, whether it
+represents a state above the critical temperature or below.  The
+configurations representing states below the critical temperature are
+called ordered states (the spins tend to point in one direction,
+resulting in a net magnetic moment) while those above the critical
+temperature are called disordered. Since a finite lattice like this
+does not exhibit a clear sign of a phase transition we will mainly
+stay with either orderer or disoredered phases. You could include the
+critical phase if you want.
 
 
-=== Part d): Classifying the Ising model phase using neural networks  ===
+Your aim here is thus to read in these data (use the examples from
+"Mehta et
+al":"https://physics.bu.edu/~pankajm/ML-Notebooks/HTML/NB_CVII-logreg_ising.html")
+and write your own code for doing logistic regression, see the lecture
+notes on "logistic
+regression":"https://compphysics.github.io/MachineLearning/doc/pub/LogReg/html/LogReg-bs.html".
+
+You should include either bootstrap or cross-validation in setting up
+your model (as done in project 1) and compute the $R2$ score and the
+mean-square error.
+We will use both ordered and disordered states to train
+the logistic regressor and, once the supervised training procedure is
+complete, you should  evaluate the performance of your classification model on
+unseen ordered, disordered and possibly critical states.  
+
+
+
+In order to find the optimal parameters of your logistic regressor you should
+include a gradient descent solver, as discussed in the "gradient
+descent
+lectures":"https://compphysics.github.io/MachineLearning/doc/pub/Splines/html/Splines-bs.html".
+Since we don't have so many data points, you may just code the
+standard gradient descent with a given learning rate, or even attempt
+to use the Newton-Raphson method.  Alternatively, it may be useful for
+the next part on neural networks to implement a stochastic gradient
+descent. For all  gradient methods, you can use _scikit-learn_'s toolbox for
+optimization methods instead of writing your own code.
+
+
+The notebook of "Mehta et al":"https://physics.bu.edu/~pankajm/ML-Notebooks/HTML/NB_CVII-logreg_ising.html" is highly recommended in order to benchmark your code and results.
+
+=== Part d): Regression analysis of the one-dimensional Ising model using neural networks  ===
+
+Your aim now, and this is the central part of this project, is to
+write to your own multilayer perceptron model implementing the back
+propagation algorithm discussed in the "lecture
+slides":"https://compphysics.github.io/MachineLearning/doc/pub/NeuralNet/html/NeuralNet-bs.html". We
+start with the regression case discussed in parts a) and b) but train
+now the network to find the optimal weights and biases. You are free
+to use the codes in the above lecture slides as starting points.
+
+Train your network and compare the results with those from your linear regression code. 
+You can test your results against a similar code using _scikit_learn_ (see the examples in teh above lecture notes) or _tensorflow/keras_. 
+
+You should have the same elements as in the regression examples, including the $R2$ score, the MSE, and bootstrap or cross-validation.
+
+
+A useful reference on the back progagation algorithm is "Nielsen's book":"http://neuralnetworksanddeeplearning.com/". It is an excellent read.
+
+=== Part e): Classifying the Ising model phase using neural networks  ===
+
+Finally, change now your cost function to the $log$ cross-entropy classification cost function for the case discussed in part c). Train your network again and
+compare the results with those from your logistic  regression code i c). 
+Here again you can compare your results with those of "Mehta et al":"https://physics.bu.edu/~pankajm/ML-Notebooks/HTML/NB_CIX-DNN_ising_TFlow.html". There they used _tensorflow_ to classify the phases. 
+
+
+
+=== Part f) Critical evaluation of the various algorithms ===
+
+After all these glorious calculations, you should now summarize the various algorithms and come with a critical evaluation of their pros and cons. Which algorithm works best for the regression case and which is best for the classification case. These codes will also be part of your final project 3, but now applied to other data sets.
+
 
-We end the classification problem of the phases of the Ising model by
-employing the algorithm for so-called feed-forward deep neural
-networks (see section 9 of Mehta *et al.*). The method is described in
-"notebook
-12":"https://physics.bu.edu/~pankajm/ML-Notebooks/HTML/NB_CIX-DNN_ising_TFlow.html".
 
-You can use tensorflow  to perform these analyses. See below for instruction on how to install tensorflow.
 
 ===== Background literature =====
 
+o  The text of Michael Nielsen is highly recommended, see "Nielsen's book":"http://neuralnetworksanddeeplearning.com/". It is an excellent read.
 
 o  The textbook of "Trevor Hastie, Robert Tibshirani, Jerome H. Friedman, The Elements of Statistical Learning, Springer":"https://www.springer.com/gp/book/9780387848570", chapters 3 and 7 are the most relevant ones for the analysis here.