lars/FYS-STK4155
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
Morten Hjorth-Jensen
2021-10-13 22:51:42 +02:00
parent d70ccf7b9a
commit 7639c59ca1
8 changed files with 225 additions and 107 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/pub/week41/html/week41-bs.html
+44 -49
View File
@@ -124,14 +124,10 @@ Automatically generated HTML file from DocOnce source
2,
None,
'then-the-first-feed-forward-pass'),
('The full Network for the Various Gates',
('The Code using Scikit-Learn',
2,
None,
'the-full-network-for-the-various-gates'),
('And the same using Scikit-Learn',
2,
None,
'and-the-same-using-scikit-learn'),
'the-code-using-scikit-learn'),
('Building neural networks in Tensorflow and Keras',
2,
None,
@@ -277,7 +273,7 @@ MathJax.Hub.Config({
<!-- navigation toc: --> <li><a href="._week41-bs006.html#example-binary-classification-problem" style="font-size: 80%;">Example: binary classification problem</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs007.html#the-softmax-function" style="font-size: 80%;">The Softmax function</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs008.html#developing-a-code-for-doing-neural-networks-with-back-propagation" style="font-size: 80%;">Developing a code for doing neural networks with back propagation</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs037.html#collect-and-pre-process-data" style="font-size: 80%;">Collect and pre-process data</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs036.html#collect-and-pre-process-data" style="font-size: 80%;">Collect and pre-process data</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs010.html#train-and-test-datasets" style="font-size: 80%;">Train and test datasets</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs011.html#define-model-and-architecture" style="font-size: 80%;">Define model and architecture</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs012.html#layers" style="font-size: 80%;">Layers</a></li>
@@ -300,47 +296,46 @@ MathJax.Hub.Config({
<!-- navigation toc: --> <li><a href="._week41-bs029.html#representing-the-data-sets" style="font-size: 80%;">Representing the Data Sets</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs030.html#setting-up-the-neural-network" style="font-size: 80%;">Setting up the Neural Network</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs031.html#then-the-first-feed-forward-pass" style="font-size: 80%;">Then the first Feed Forward pass</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs032.html#the-full-network-for-the-various-gates" style="font-size: 80%;">The full Network for the Various Gates</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs033.html#and-the-same-using-scikit-learn" style="font-size: 80%;">And the same using Scikit-Learn</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs034.html#building-neural-networks-in-tensorflow-and-keras" style="font-size: 80%;">Building neural networks in Tensorflow and Keras</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs035.html#tensorflow" style="font-size: 80%;">Tensorflow</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs036.html#using-keras" style="font-size: 80%;">Using Keras</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs037.html#collect-and-pre-process-data" style="font-size: 80%;">Collect and pre-process data</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs038.html#the-breast-cancer-data-now-with-keras" style="font-size: 80%;">The Breast Cancer Data, now with Keras</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs039.html#fine-tuning-neural-network-hyperparameters" style="font-size: 80%;">Fine-tuning neural network hyperparameters</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs040.html#hidden-layers" style="font-size: 80%;">Hidden layers</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs041.html#which-activation-function-should-i-use" style="font-size: 80%;">Which activation function should I use?</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs042.html#is-the-logistic-activation-function-sigmoid-our-choice" style="font-size: 80%;">Is the Logistic activation function (Sigmoid) our choice?</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs043.html#the-derivative-of-the-logistic-funtion" style="font-size: 80%;">The derivative of the Logistic funtion</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs044.html#the-relu-function-family" style="font-size: 80%;">The RELU function family</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs045.html#which-activation-function-should-we-use" style="font-size: 80%;">Which activation function should we use?</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs046.html#more-on-activation-functions-output-layers" style="font-size: 80%;">More on activation functions, output layers</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs047.html#batch-normalization" style="font-size: 80%;">Batch Normalization</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs048.html#dropout" style="font-size: 80%;">Dropout</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs049.html#gradient-clipping" style="font-size: 80%;">Gradient Clipping</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs050.html#a-very-nice-website-on-neural-networks" style="font-size: 80%;">A very nice website on Neural Networks</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs051.html#a-top-down-perspective-on-neural-networks" style="font-size: 80%;">A top-down perspective on Neural networks</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs052.html#limitations-of-supervised-learning-with-deep-networks" style="font-size: 80%;">Limitations of supervised learning with deep networks</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs053.html#overarching-views-a-personal-note" style="font-size: 80%;">Overarching Views, a personal note</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs054.html#from-a-spherical-cow-to-a-real-one" style="font-size: 80%;">From a Spherical Cow to a real one</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs055.html#convolutional-neural-networks-recognizing-images" style="font-size: 80%;">Convolutional Neural Networks (recognizing images)</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs056.html#regular-nns-don-t-scale-well-to-full-images" style="font-size: 80%;">Regular NNs don’t scale well to full images</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs057.html#3d-volumes-of-neurons" style="font-size: 80%;">3D volumes of neurons</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs058.html#layers-used-to-build-cnns" style="font-size: 80%;">Layers used to build CNNs</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs059.html#transforming-images" style="font-size: 80%;">Transforming images</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs060.html#cnns-in-brief" style="font-size: 80%;">CNNs in brief</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs061.html#cnns-in-more-detail-building-convolutional-neural-networks-in-tensorflow-and-keras" style="font-size: 80%;">CNNs in more detail, building convolutional neural networks in Tensorflow and Keras</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs062.html#setting-it-up" style="font-size: 80%;">Setting it up</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs063.html#the-mnist-dataset-again" style="font-size: 80%;">The MNIST dataset again</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs064.html#strong-correlations" style="font-size: 80%;">Strong correlations</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs065.html#layers-of-a-cnn" style="font-size: 80%;">Layers of a CNN</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs066.html#systematic-reduction" style="font-size: 80%;">Systematic reduction</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs067.html#prerequisites-collect-and-pre-process-data" style="font-size: 80%;">Prerequisites: Collect and pre-process data</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs068.html#importing-keras-and-tensorflow" style="font-size: 80%;">Importing Keras and Tensorflow</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs069.html#running-with-keras" style="font-size: 80%;">Running with Keras</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs070.html#final-part" style="font-size: 80%;">Final part</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs071.html#final-visualization" style="font-size: 80%;">Final visualization</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs072.html#fun-links" style="font-size: 80%;">Fun links</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs032.html#the-code-using-scikit-learn" style="font-size: 80%;">The Code using Scikit-Learn</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs033.html#building-neural-networks-in-tensorflow-and-keras" style="font-size: 80%;">Building neural networks in Tensorflow and Keras</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs034.html#tensorflow" style="font-size: 80%;">Tensorflow</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs035.html#using-keras" style="font-size: 80%;">Using Keras</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs036.html#collect-and-pre-process-data" style="font-size: 80%;">Collect and pre-process data</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs037.html#the-breast-cancer-data-now-with-keras" style="font-size: 80%;">The Breast Cancer Data, now with Keras</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs038.html#fine-tuning-neural-network-hyperparameters" style="font-size: 80%;">Fine-tuning neural network hyperparameters</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs039.html#hidden-layers" style="font-size: 80%;">Hidden layers</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs040.html#which-activation-function-should-i-use" style="font-size: 80%;">Which activation function should I use?</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs041.html#is-the-logistic-activation-function-sigmoid-our-choice" style="font-size: 80%;">Is the Logistic activation function (Sigmoid) our choice?</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs042.html#the-derivative-of-the-logistic-funtion" style="font-size: 80%;">The derivative of the Logistic funtion</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs043.html#the-relu-function-family" style="font-size: 80%;">The RELU function family</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs044.html#which-activation-function-should-we-use" style="font-size: 80%;">Which activation function should we use?</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs045.html#more-on-activation-functions-output-layers" style="font-size: 80%;">More on activation functions, output layers</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs046.html#batch-normalization" style="font-size: 80%;">Batch Normalization</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs047.html#dropout" style="font-size: 80%;">Dropout</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs048.html#gradient-clipping" style="font-size: 80%;">Gradient Clipping</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs049.html#a-very-nice-website-on-neural-networks" style="font-size: 80%;">A very nice website on Neural Networks</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs050.html#a-top-down-perspective-on-neural-networks" style="font-size: 80%;">A top-down perspective on Neural networks</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs051.html#limitations-of-supervised-learning-with-deep-networks" style="font-size: 80%;">Limitations of supervised learning with deep networks</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs052.html#overarching-views-a-personal-note" style="font-size: 80%;">Overarching Views, a personal note</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs053.html#from-a-spherical-cow-to-a-real-one" style="font-size: 80%;">From a Spherical Cow to a real one</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs054.html#convolutional-neural-networks-recognizing-images" style="font-size: 80%;">Convolutional Neural Networks (recognizing images)</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs055.html#regular-nns-don-t-scale-well-to-full-images" style="font-size: 80%;">Regular NNs don’t scale well to full images</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs056.html#3d-volumes-of-neurons" style="font-size: 80%;">3D volumes of neurons</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs057.html#layers-used-to-build-cnns" style="font-size: 80%;">Layers used to build CNNs</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs058.html#transforming-images" style="font-size: 80%;">Transforming images</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs059.html#cnns-in-brief" style="font-size: 80%;">CNNs in brief</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs060.html#cnns-in-more-detail-building-convolutional-neural-networks-in-tensorflow-and-keras" style="font-size: 80%;">CNNs in more detail, building convolutional neural networks in Tensorflow and Keras</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs061.html#setting-it-up" style="font-size: 80%;">Setting it up</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs062.html#the-mnist-dataset-again" style="font-size: 80%;">The MNIST dataset again</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs063.html#strong-correlations" style="font-size: 80%;">Strong correlations</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs064.html#layers-of-a-cnn" style="font-size: 80%;">Layers of a CNN</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs065.html#systematic-reduction" style="font-size: 80%;">Systematic reduction</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs066.html#prerequisites-collect-and-pre-process-data" style="font-size: 80%;">Prerequisites: Collect and pre-process data</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs067.html#importing-keras-and-tensorflow" style="font-size: 80%;">Importing Keras and Tensorflow</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs068.html#running-with-keras" style="font-size: 80%;">Running with Keras</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs069.html#final-part" style="font-size: 80%;">Final part</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs070.html#final-visualization" style="font-size: 80%;">Final visualization</a></li>
<!-- navigation toc: --> <li><a href="._week41-bs071.html#fun-links" style="font-size: 80%;">Fun links</a></li>
</ul>
</li>
@@ -399,7 +394,7 @@ MathJax.Hub.Config({
<li><a href="._week41-bs008.html">9</a></li>
<li><a href="._week41-bs009.html">10</a></li>
<li><a href="">...</a></li>
<li><a href="._week41-bs072.html">73</a></li>
<li><a href="._week41-bs071.html">72</a></li>
<li><a href="._week41-bs001.html">&raquo;</a></li>
</ul>
<!-- ------------------- end of main content --------------- -->
doc/pub/week41/html/week41-reveal.html
+1 -11
View File
@@ -1639,17 +1639,7 @@ Not an impressive result, but this was our first forward pass with randomly assi
<section>
<h2 id="the-full-network-for-the-various-gates">The full Network for the Various Gates </h2>
<p>
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
<div class="highlight" style="background: #eeeedd"><pre style="font-size: 80%; line-height: 125%;"><span></span>
</pre></div>
</section>
<section>
<h2 id="and-the-same-using-scikit-learn">And the same using Scikit-Learn </h2>
<h2 id="the-code-using-scikit-learn">The Code using Scikit-Learn </h2>
<p>
doc/pub/week41/html/week41-solarized.html
+3 -16
View File
@@ -144,14 +144,10 @@ div { text-align: justify; text-justify: inter-word; }
2,
None,
'then-the-first-feed-forward-pass'),
('The full Network for the Various Gates',
('The Code using Scikit-Learn',
2,
None,
'the-full-network-for-the-various-gates'),
('And the same using Scikit-Learn',
2,
None,
'and-the-same-using-scikit-learn'),
'the-code-using-scikit-learn'),
('Building neural networks in Tensorflow and Keras',
2,
None,
@@ -1655,16 +1651,7 @@ Not an impressive result, but this was our first forward pass with randomly assi
<p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
<h2 id="the-full-network-for-the-various-gates">The full Network for the Various Gates </h2>
<p>
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
<div class="highlight" style="background: #eeeedd"><pre style="line-height: 125%;"><span></span>
</pre></div>
<p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
<h2 id="and-the-same-using-scikit-learn">And the same using Scikit-Learn </h2>
<h2 id="the-code-using-scikit-learn">The Code using Scikit-Learn </h2>
<p>
doc/pub/week41/html/week41.html
+3 -16
View File
@@ -149,14 +149,10 @@ div { text-align: justify; text-justify: inter-word; }
2,
None,
'then-the-first-feed-forward-pass'),
('The full Network for the Various Gates',
('The Code using Scikit-Learn',
2,
None,
'the-full-network-for-the-various-gates'),
('And the same using Scikit-Learn',
2,
None,
'and-the-same-using-scikit-learn'),
'the-code-using-scikit-learn'),
('Building neural networks in Tensorflow and Keras',
2,
None,
@@ -1660,16 +1656,7 @@ Not an impressive result, but this was our first forward pass with randomly assi
<p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
<h2 id="the-full-network-for-the-various-gates">The full Network for the Various Gates </h2>
<p>
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%;"><span></span>
</pre></div>
<p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
<h2 id="and-the-same-using-scikit-learn">And the same using Scikit-Learn </h2>
<h2 id="the-code-using-scikit-learn">The Code using Scikit-Learn </h2>
<p>
doc/pub/week41/ipynb/ipynb-week41-src.tar.gz
BIN
View File
Binary file not shown.
doc/pub/week41/ipynb/week41.ipynb
+1 -8
View File
@@ -1564,14 +1564,7 @@
"source": [
"Not an impressive result, but this was our first forward pass with randomly assigned weights. Let us now add the full network with the back-propagation algorithm discussed above.\n",
"\n",
"## The full Network for the Various Gates"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## And the same using Scikit-Learn"
"## The Code using Scikit-Learn"
]
},
{
doc/src/week41/programs/nnown.py
+172
View File
@@ -0,0 +1,172 @@
# import necessary packages
import numpy as np
import matplotlib.pyplot as plt
from sklearn.neural_network import MLPClassifier
from sklearn.metrics import accuracy_score
import seaborn as sns
# ensure the same random numbers appear every time
np.random.seed(0)
# Design matrix
X = np.array([ [0, 0], [0, 1], [1, 0],[1, 1]],dtype=np.float64)
# The XOR gate
yXOR = np.array( [ 0, 1 ,1, 0])
# The OR gate
yOR = np.array( [ 0, 1 ,1, 1])
# The AND gate
yAND = np.array( [ 0, 0 ,0, 1])
# Defining the neural network
n_inputs, n_features = X.shape
n_hidden_neurons = 2
n_categories = 2
n_features = 2
def sigmoid(x):
return 1/(1 + np.exp(-x))
class NeuralNetwork:
def __init__(
self,
X_data,
Y_data,
n_hidden_neurons=2,
n_categories=2,
epochs=10,
batch_size=100,
eta=0.1,
lmbd=0.0):
self.X_data_full = X_data
self.Y_data_full = Y_data
self.n_inputs = X_data.shape[0]
self.n_features = X_data.shape[1]
self.n_hidden_neurons = n_hidden_neurons
self.n_categories = n_categories
self.epochs = epochs
self.batch_size = batch_size
self.iterations = self.n_inputs // self.batch_size
self.eta = eta
self.lmbd = lmbd
self.create_biases_and_weights()
def create_biases_and_weights(self):
self.hidden_weights = np.random.randn(self.n_features, self.n_hidden_neurons)
self.hidden_bias = np.zeros(self.n_hidden_neurons) + 0.01
self.output_weights = np.random.randn(self.n_hidden_neurons, self.n_categories)
self.output_bias = np.zeros(self.n_categories) + 0.01
def feed_forward(self):
# feed-forward for training
self.z_h = np.matmul(self.X_data, self.hidden_weights) + self.hidden_bias
self.a_h = sigmoid(self.z_h)
self.z_o = np.matmul(self.a_h, self.output_weights) + self.output_bias
exp_term = sigmoid(self.z_o)
self.probabilities = exp_term
def feed_forward_out(self, X):
# feed-forward for output
z_h = np.matmul(X, self.hidden_weights) + self.hidden_bias
a_h = sigmoid(z_h)
z_o = np.matmul(a_h, self.output_weights) + self.output_bias
exp_term = sigmoid(z_o)
probabilities = exp_term
return probabilities
def backpropagation(self):
error_output = self.probabilities - self.Y_data
error_hidden = np.matmul(error_output, self.output_weights.T) * self.a_h * (1 - self.a_h)
self.output_weights_gradient = np.matmul(self.a_h.T, error_output)
self.output_bias_gradient = np.sum(error_output, axis=0)
self.hidden_weights_gradient = np.matmul(self.X_data.T, error_hidden)
self.hidden_bias_gradient = np.sum(error_hidden, axis=0)
if self.lmbd > 0.0:
self.output_weights_gradient += self.lmbd * self.output_weights
self.hidden_weights_gradient += self.lmbd * self.hidden_weights
self.output_weights -= self.eta * self.output_weights_gradient
self.output_bias -= self.eta * self.output_bias_gradient
self.hidden_weights -= self.eta * self.hidden_weights_gradient
self.hidden_bias -= self.eta * self.hidden_bias_gradient
def predict(self, X):
probabilities = self.feed_forward_out(X)
return np.argmax(probabilities, axis=1)
def predict_probabilities(self, X):
probabilities = self.feed_forward_out(X)
return probabilities
def train(self):
data_indices = np.arange(self.n_inputs)
for i in range(self.epochs):
for j in range(self.iterations):
# pick datapoints with replacement
chosen_datapoints = np.random.choice(
data_indices, size=self.batch_size, replace=False
)
# minibatch training data
self.X_data = self.X_data_full[chosen_datapoints]
self.Y_data = self.Y_data_full[chosen_datapoints]
self.feed_forward()
self.backpropagation()
epochs = 100
batch_size = 100
eta_vals = np.logspace(-5, 1, 7)
lmbd_vals = np.logspace(-5, 1, 7)
# store the models for later use
DNN_numpy = np.zeros((len(eta_vals), len(lmbd_vals)), dtype=object)
# grid search
for i, eta in enumerate(eta_vals):
for j, lmbd in enumerate(lmbd_vals):
dnn = NeuralNetwork(X, yXOR, eta=eta, lmbd=lmbd, epochs=epochs, batch_size=batch_size,
n_hidden_neurons=n_hidden_neurons, n_categories=n_categories)
dnn.train()
DNN_numpy[i][j] = dnn
test_predict = dnn.predict(X)
print("Learning rate = ", eta)
print("Lambda = ", lmbd)
print("Accuracy score on test set: ", accuracy_score(yXOR, test_predict))
print()
sns.set()
test_accuracy = np.zeros((len(eta_vals), len(lmbd_vals)))
for i in range(len(eta_vals)):
for j in range(len(lmbd_vals)):
dnn = DNN_numpy[i][j]
test_pred = dnn.predict(X)
test_accuracy[i][j] = accuracy_score(yXOR, test_pred)
fig, ax = plt.subplots(figsize = (10, 10))
sns.heatmap(test_accuracy, annot=True, ax=ax, cmap="viridis")
ax.set_title("Test Accuracy")
ax.set_ylabel("$\eta$")
ax.set_xlabel("$\lambda$")
plt.show()
doc/src/week41/week41.do.txt
+1 -7
View File
@@ -1207,13 +1207,7 @@ print(predictions)
Not an impressive result, but this was our first forward pass with randomly assigned weights. Let us now add the full network with the back-propagation algorithm discussed above.
!split
===== The full Network for the Various Gates =====
!bc pycod
!ec
!split
===== And the same using Scikit-Learn =====
===== The Code using Scikit-Learn =====
!bc pycod