diff --git a/doc/LectureNotes/_build/.doctrees/chapter1.doctree b/doc/LectureNotes/_build/.doctrees/chapter1.doctree index c31353833..e99fc1f1b 100644 Binary files a/doc/LectureNotes/_build/.doctrees/chapter1.doctree and b/doc/LectureNotes/_build/.doctrees/chapter1.doctree differ diff --git a/doc/LectureNotes/_build/.doctrees/chapter10.doctree b/doc/LectureNotes/_build/.doctrees/chapter10.doctree index f4681a24c..1871bcae1 100644 Binary files a/doc/LectureNotes/_build/.doctrees/chapter10.doctree and b/doc/LectureNotes/_build/.doctrees/chapter10.doctree differ diff --git a/doc/LectureNotes/_build/.doctrees/environment.pickle b/doc/LectureNotes/_build/.doctrees/environment.pickle deleted file mode 100644 index fbbc2f22f..000000000 Binary files a/doc/LectureNotes/_build/.doctrees/environment.pickle and /dev/null differ diff --git a/doc/LectureNotes/_build/jupyter_execute/chapter1.ipynb b/doc/LectureNotes/_build/jupyter_execute/chapter1.ipynb index 69fd6ba8c..a355ce8bd 100644 --- a/doc/LectureNotes/_build/jupyter_execute/chapter1.ipynb +++ b/doc/LectureNotes/_build/jupyter_execute/chapter1.ipynb @@ -343,7 +343,7 @@ "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -515,7 +515,7 @@ "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -583,18 +583,18 @@ "output_type": "stream", "text": [ "The intercept alpha: \n", - " [2.04292593]\n", + " [1.9480732]\n", "Coefficient beta : \n", - " [[5.00440395]]\n", - "Mean squared error: 0.27\n", - "Variance score: 0.88\n", + " [[4.96645032]]\n", + "Mean squared error: 0.20\n", + "Variance score: 0.91\n", "Mean squared log error: 0.01\n", - "Mean absolute error: 0.41\n" + "Mean absolute error: 0.35\n" ] }, { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -822,7 +822,7 @@ "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] diff --git a/doc/LectureNotes/_build/jupyter_execute/chapter10.ipynb b/doc/LectureNotes/_build/jupyter_execute/chapter10.ipynb index e88ed2210..d7dd1acac 100644 --- a/doc/LectureNotes/_build/jupyter_execute/chapter10.ipynb +++ b/doc/LectureNotes/_build/jupyter_execute/chapter10.ipynb @@ -1077,7 +1077,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_18986/953065564.py:4: RuntimeWarning: overflow encountered in exp\n", + "/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_31323/953065564.py:4: RuntimeWarning: overflow encountered in exp\n", " return 1/(1 + np.exp(-x))\n" ] }, @@ -1451,6 +1451,304 @@ "\n" ] }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.0001\n", + "Lambda = 0.0001\n", + "Accuracy score on test set: 0.5944444444444444\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.0001\n", + "Lambda = 0.001\n", + "Accuracy score on test set: 0.5888888888888889\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.0001\n", + "Lambda = 0.01\n", + "Accuracy score on test set: 0.6111111111111112\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.0001\n", + "Lambda = 0.1\n", + "Accuracy score on test set: 0.5222222222222223\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.0001\n", + "Lambda = 1.0\n", + "Accuracy score on test set: 0.5555555555555556\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.0001\n", + "Lambda = 10.0\n", + "Accuracy score on test set: 0.8055555555555556\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.001\n", + "Lambda = 1e-05\n", + "Accuracy score on test set: 0.85\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.001\n", + "Lambda = 0.0001\n", + "Accuracy score on test set: 0.85\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.001\n", + "Lambda = 0.001\n", + "Accuracy score on test set: 0.875\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.001\n", + "Lambda = 0.01\n", + "Accuracy score on test set: 0.8666666666666667\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.001\n", + "Lambda = 0.1\n", + "Accuracy score on test set: 0.8638888888888889\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.001\n", + "Lambda = 1.0\n", + "Accuracy score on test set: 0.9555555555555556\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.001\n", + "Lambda = 10.0\n", + "Accuracy score on test set: 0.925\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.01\n", + "Lambda = 1e-05\n", + "Accuracy score on test set: 0.9472222222222222\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.01\n", + "Lambda = 0.0001\n", + "Accuracy score on test set: 0.9277777777777778\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.01\n", + "Lambda = 0.001\n", + "Accuracy score on test set: 0.9472222222222222\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.01\n", + "Lambda = 0.01\n", + "Accuracy score on test set: 0.9305555555555556\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.01\n", + "Lambda = 0.1\n", + "Accuracy score on test set: 0.9555555555555556\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.01\n", + "Lambda = 1.0\n", + "Accuracy score on test set: 0.7694444444444445\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.01\n", + "Lambda = 10.0\n", + "Accuracy score on test set: 0.19166666666666668\n", + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_31323/953065564.py:4: RuntimeWarning: overflow encountered in exp\n", + " return 1/(1 + np.exp(-x))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.1\n", + "Lambda = 1e-05\n", + "Accuracy score on test set: 0.10555555555555556\n", + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_31323/953065564.py:4: RuntimeWarning: overflow encountered in exp\n", + " return 1/(1 + np.exp(-x))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.1\n", + "Lambda = 0.0001\n", + "Accuracy score on test set: 0.08611111111111111\n", + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_31323/953065564.py:4: RuntimeWarning: overflow encountered in exp\n", + " return 1/(1 + np.exp(-x))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.1\n", + "Lambda = 0.001\n", + "Accuracy score on test set: 0.10555555555555556\n", + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_31323/953065564.py:4: RuntimeWarning: overflow encountered in exp\n", + " return 1/(1 + np.exp(-x))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.1\n", + "Lambda = 0.01\n", + "Accuracy score on test set: 0.08888888888888889\n", + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_31323/953065564.py:4: RuntimeWarning: overflow encountered in exp\n", + " return 1/(1 + np.exp(-x))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Learning rate = 0.1\n", + "Lambda = 0.1\n", + "Accuracy score on test set: 0.08611111111111111\n", + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_31323/953065564.py:4: RuntimeWarning: overflow encountered in exp\n", + " return 1/(1 + np.exp(-x))\n" + ] + }, { "ename": "KeyboardInterrupt", "evalue": "", diff --git a/doc/LectureNotes/_build/jupyter_execute/chapter1_17_0.png b/doc/LectureNotes/_build/jupyter_execute/chapter1_17_0.png index c9c11014c..d75a08c29 100644 Binary files a/doc/LectureNotes/_build/jupyter_execute/chapter1_17_0.png and b/doc/LectureNotes/_build/jupyter_execute/chapter1_17_0.png differ diff --git a/doc/LectureNotes/_build/jupyter_execute/chapter1_19_1.png b/doc/LectureNotes/_build/jupyter_execute/chapter1_19_1.png index dbb2f9029..93dbc6cdc 100644 Binary files a/doc/LectureNotes/_build/jupyter_execute/chapter1_19_1.png and b/doc/LectureNotes/_build/jupyter_execute/chapter1_19_1.png differ diff --git a/doc/LectureNotes/_build/jupyter_execute/chapter1_33_0.png b/doc/LectureNotes/_build/jupyter_execute/chapter1_33_0.png index ababfc878..aa7e4746f 100644 Binary files a/doc/LectureNotes/_build/jupyter_execute/chapter1_33_0.png and b/doc/LectureNotes/_build/jupyter_execute/chapter1_33_0.png differ diff --git a/doc/LectureNotes/_build/jupyter_execute/chapter1_68_7.png b/doc/LectureNotes/_build/jupyter_execute/chapter1_68_7.png new file mode 100644 index 000000000..f5d912f6a Binary files /dev/null and b/doc/LectureNotes/_build/jupyter_execute/chapter1_68_7.png differ diff --git a/doc/LectureNotes/_build/jupyter_execute/chapter1_9_0.png b/doc/LectureNotes/_build/jupyter_execute/chapter1_9_0.png index 62cdabb05..3958a79c4 100644 Binary files a/doc/LectureNotes/_build/jupyter_execute/chapter1_9_0.png and b/doc/LectureNotes/_build/jupyter_execute/chapter1_9_0.png differ diff --git a/doc/LectureNotes/_toc.yml b/doc/LectureNotes/_toc.yml index 17aef2496..25f6d8f6a 100644 --- a/doc/LectureNotes/_toc.yml +++ b/doc/LectureNotes/_toc.yml @@ -56,8 +56,10 @@ parts: - file: week40.ipynb - file: exercisesweek41.ipynb - file: week41.ipynb + - file: exercisesweek42.ipynb + - file: week42.ipynb - caption: Projects numbered: false chapters: - file: project1.ipynb - = file: project2.ipynb + - file: project2.ipynb diff --git a/doc/LectureNotes/week42.ipynb b/doc/LectureNotes/week42.ipynb index a55b73018..adc0b59eb 100644 --- a/doc/LectureNotes/week42.ipynb +++ b/doc/LectureNotes/week42.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "markdown", - "id": "6f748484", + "id": "d2a36f3c", "metadata": { "editable": true }, @@ -14,7 +14,7 @@ }, { "cell_type": "markdown", - "id": "a2333337", + "id": "310c269f", "metadata": { "editable": true }, @@ -22,12 +22,12 @@ "# Week 42 Constructing a Neural Network code with introduction to Tensor flow\n", "**Morten Hjorth-Jensen**, Department of Physics, University of Oslo and Department of Physics and Astronomy and Facility for Rare Isotope Beams, Michigan State University\n", "\n", - "Date: **Week 42**" + "Date: **October 16-20, 2023**" ] }, { "cell_type": "markdown", - "id": "0afbab80", + "id": "427a552f", "metadata": { "editable": true }, @@ -69,17 +69,17 @@ }, { "cell_type": "markdown", - "id": "218979dd", + "id": "b53157af", "metadata": { "editable": true }, "source": [ - "## Lecture Thursday October 12" + "## Lecture Thursday October 19" ] }, { "cell_type": "markdown", - "id": "0bc89100", + "id": "9002bf39", "metadata": { "editable": true }, @@ -94,7 +94,7 @@ }, { "cell_type": "markdown", - "id": "878894aa", + "id": "228a98c1", "metadata": { "editable": true }, @@ -117,7 +117,7 @@ }, { "cell_type": "markdown", - "id": "77f6818e", + "id": "c38b5eaf", "metadata": { "editable": true }, @@ -129,7 +129,7 @@ }, { "cell_type": "markdown", - "id": "44a6eb1e", + "id": "991e9164", "metadata": { "editable": true }, @@ -139,7 +139,7 @@ }, { "cell_type": "markdown", - "id": "bde0c34a", + "id": "b5c5f27f", "metadata": { "editable": true }, @@ -151,7 +151,7 @@ }, { "cell_type": "markdown", - "id": "95ad0241", + "id": "41dd527c", "metadata": { "editable": true }, @@ -161,7 +161,7 @@ }, { "cell_type": "markdown", - "id": "9487e01a", + "id": "49fa0a94", "metadata": { "editable": true }, @@ -173,7 +173,7 @@ }, { "cell_type": "markdown", - "id": "2763e7bc", + "id": "da9bdf96", "metadata": { "editable": true }, @@ -185,7 +185,7 @@ }, { "cell_type": "markdown", - "id": "c4ba4400", + "id": "7e012a3c", "metadata": { "editable": true }, @@ -196,7 +196,7 @@ }, { "cell_type": "markdown", - "id": "4623a430", + "id": "a10b5095", "metadata": { "editable": true }, @@ -224,7 +224,7 @@ }, { "cell_type": "markdown", - "id": "73be143c", + "id": "dae5d47e", "metadata": { "editable": true }, @@ -236,7 +236,7 @@ }, { "cell_type": "markdown", - "id": "88b61ced", + "id": "2b98a58c", "metadata": { "editable": true }, @@ -246,7 +246,7 @@ }, { "cell_type": "markdown", - "id": "36e7d5b4", + "id": "d44d09a5", "metadata": { "editable": true }, @@ -258,7 +258,7 @@ }, { "cell_type": "markdown", - "id": "2132d8d9", + "id": "deac74cc", "metadata": { "editable": true }, @@ -269,7 +269,7 @@ }, { "cell_type": "markdown", - "id": "e73b584a", + "id": "9346792f", "metadata": { "editable": true }, @@ -281,7 +281,7 @@ }, { "cell_type": "markdown", - "id": "ead64ff0", + "id": "cd47740a", "metadata": { "editable": true }, @@ -294,7 +294,7 @@ }, { "cell_type": "markdown", - "id": "175865ba", + "id": "624d266a", "metadata": { "editable": true }, @@ -319,7 +319,7 @@ }, { "cell_type": "markdown", - "id": "8ff83c23", + "id": "ab1fdd1f", "metadata": { "editable": true }, @@ -332,7 +332,7 @@ }, { "cell_type": "markdown", - "id": "e4e3e3ae", + "id": "a005eeef", "metadata": { "editable": true }, @@ -344,7 +344,7 @@ }, { "cell_type": "markdown", - "id": "9bb50a82", + "id": "0d9e3087", "metadata": { "editable": true }, @@ -356,7 +356,7 @@ }, { "cell_type": "markdown", - "id": "0df7623e", + "id": "308b820e", "metadata": { "editable": true }, @@ -366,7 +366,7 @@ }, { "cell_type": "markdown", - "id": "007c5ccb", + "id": "ae243251", "metadata": { "editable": true }, @@ -378,7 +378,7 @@ }, { "cell_type": "markdown", - "id": "46517787", + "id": "79055e74", "metadata": { "editable": true }, @@ -390,7 +390,7 @@ }, { "cell_type": "markdown", - "id": "2e5272ee", + "id": "fa673507", "metadata": { "editable": true }, @@ -402,7 +402,7 @@ }, { "cell_type": "markdown", - "id": "c4c9df05", + "id": "4cc3f2e2", "metadata": { "editable": true }, @@ -414,7 +414,7 @@ }, { "cell_type": "markdown", - "id": "f31ae9bc", + "id": "28883e22", "metadata": { "editable": true }, @@ -424,7 +424,7 @@ }, { "cell_type": "markdown", - "id": "c0f2db30", + "id": "c2563a79", "metadata": { "editable": true }, @@ -436,7 +436,7 @@ }, { "cell_type": "markdown", - "id": "b0a4e033", + "id": "f267068b", "metadata": { "editable": true }, @@ -446,7 +446,7 @@ }, { "cell_type": "markdown", - "id": "c6d9a957", + "id": "8a4a0387", "metadata": { "editable": true }, @@ -458,7 +458,7 @@ }, { "cell_type": "markdown", - "id": "6a2015ea", + "id": "19fb027a", "metadata": { "editable": true }, @@ -471,7 +471,7 @@ }, { "cell_type": "markdown", - "id": "9095b828", + "id": "f41bc98e", "metadata": { "editable": true }, @@ -483,7 +483,7 @@ }, { "cell_type": "markdown", - "id": "3fcc73a0", + "id": "23638b6a", "metadata": { "editable": true }, @@ -493,7 +493,7 @@ }, { "cell_type": "markdown", - "id": "0a29ae09", + "id": "d3f6e3e3", "metadata": { "editable": true }, @@ -505,7 +505,7 @@ }, { "cell_type": "markdown", - "id": "98d33296", + "id": "61c4f101", "metadata": { "editable": true }, @@ -516,7 +516,7 @@ }, { "cell_type": "markdown", - "id": "429ed394", + "id": "58ac0397", "metadata": { "editable": true }, @@ -528,7 +528,7 @@ }, { "cell_type": "markdown", - "id": "2a5136a4", + "id": "585c0850", "metadata": { "editable": true }, @@ -538,7 +538,7 @@ }, { "cell_type": "markdown", - "id": "192baba3", + "id": "f6b1c1c8", "metadata": { "editable": true }, @@ -550,7 +550,7 @@ }, { "cell_type": "markdown", - "id": "31947c1f", + "id": "97ae8668", "metadata": { "editable": true }, @@ -560,7 +560,7 @@ }, { "cell_type": "markdown", - "id": "ccabb47b", + "id": "28f524e4", "metadata": { "editable": true }, @@ -571,7 +571,7 @@ }, { "cell_type": "markdown", - "id": "637e9a4f", + "id": "233b736f", "metadata": { "editable": true }, @@ -584,7 +584,7 @@ }, { "cell_type": "markdown", - "id": "72777fcb", + "id": "f0e7c038", "metadata": { "editable": true }, @@ -594,7 +594,7 @@ }, { "cell_type": "markdown", - "id": "acae325f", + "id": "d17816a2", "metadata": { "editable": true }, @@ -606,7 +606,7 @@ }, { "cell_type": "markdown", - "id": "4e52aa77", + "id": "1a196a75", "metadata": { "editable": true }, @@ -616,7 +616,7 @@ }, { "cell_type": "markdown", - "id": "14ede160", + "id": "b2dcca96", "metadata": { "editable": true }, @@ -628,7 +628,7 @@ }, { "cell_type": "markdown", - "id": "8eed9d34", + "id": "1f8acea2", "metadata": { "editable": true }, @@ -638,7 +638,7 @@ }, { "cell_type": "markdown", - "id": "ad7bcdbc", + "id": "4adc4dc7", "metadata": { "editable": true }, @@ -662,7 +662,7 @@ }, { "cell_type": "markdown", - "id": "c6a34b9d", + "id": "17f30edb", "metadata": { "editable": true }, @@ -712,7 +712,7 @@ { "cell_type": "code", "execution_count": 1, - "id": "98bdaf7c", + "id": "69ec827f", "metadata": { "collapsed": false, "editable": true @@ -767,7 +767,7 @@ }, { "cell_type": "markdown", - "id": "ee64810c", + "id": "867080d1", "metadata": { "editable": true }, @@ -788,7 +788,7 @@ { "cell_type": "code", "execution_count": 2, - "id": "09b3024d", + "id": "1659b538", "metadata": { "collapsed": false, "editable": true @@ -826,7 +826,7 @@ }, { "cell_type": "markdown", - "id": "17382aef", + "id": "304e16d9", "metadata": { "editable": true }, @@ -870,7 +870,7 @@ }, { "cell_type": "markdown", - "id": "1f8a5a07", + "id": "73aaf166", "metadata": { "editable": true }, @@ -910,7 +910,7 @@ }, { "cell_type": "markdown", - "id": "679bc5ef", + "id": "302a43c9", "metadata": { "editable": true }, @@ -931,7 +931,7 @@ { "cell_type": "code", "execution_count": 3, - "id": "31947cdb", + "id": "20c961e1", "metadata": { "collapsed": false, "editable": true @@ -957,7 +957,7 @@ }, { "cell_type": "markdown", - "id": "10bf669a", + "id": "b63a63bc", "metadata": { "editable": true }, @@ -985,7 +985,7 @@ }, { "cell_type": "markdown", - "id": "4f812b1d", + "id": "a1ee6c2a", "metadata": { "editable": true }, @@ -1022,7 +1022,7 @@ { "cell_type": "code", "execution_count": 4, - "id": "c7f08a08", + "id": "85e741aa", "metadata": { "collapsed": false, "editable": true @@ -1068,7 +1068,7 @@ }, { "cell_type": "markdown", - "id": "51211bf4", + "id": "618d4858", "metadata": { "editable": true }, @@ -1099,7 +1099,7 @@ }, { "cell_type": "markdown", - "id": "0c28bf7b", + "id": "7c098021", "metadata": { "editable": true }, @@ -1137,7 +1137,7 @@ }, { "cell_type": "markdown", - "id": "0357f19f", + "id": "bcfe9ca6", "metadata": { "editable": true }, @@ -1171,7 +1171,7 @@ }, { "cell_type": "markdown", - "id": "c45865cf", + "id": "be9470b3", "metadata": { "editable": true }, @@ -1212,7 +1212,7 @@ { "cell_type": "code", "execution_count": 5, - "id": "e0641df5", + "id": "3b549560", "metadata": { "collapsed": false, "editable": true @@ -1291,7 +1291,7 @@ }, { "cell_type": "markdown", - "id": "feebbdcb", + "id": "70834cc0", "metadata": { "editable": true }, @@ -1312,7 +1312,7 @@ }, { "cell_type": "markdown", - "id": "a9fce5a7", + "id": "feb328ab", "metadata": { "editable": true }, @@ -1326,7 +1326,7 @@ { "cell_type": "code", "execution_count": 6, - "id": "88ce9dfc", + "id": "bd075104", "metadata": { "collapsed": false, "editable": true @@ -1436,7 +1436,7 @@ }, { "cell_type": "markdown", - "id": "e9abf91b", + "id": "0b719fba", "metadata": { "editable": true }, @@ -1455,7 +1455,7 @@ { "cell_type": "code", "execution_count": 7, - "id": "841bda7c", + "id": "78fbbfb2", "metadata": { "collapsed": false, "editable": true @@ -1482,7 +1482,7 @@ }, { "cell_type": "markdown", - "id": "6bb4719d", + "id": "bcce4264", "metadata": { "editable": true }, @@ -1496,7 +1496,7 @@ { "cell_type": "code", "execution_count": 8, - "id": "3d940b93", + "id": "a8928377", "metadata": { "collapsed": false, "editable": true @@ -1527,7 +1527,7 @@ }, { "cell_type": "markdown", - "id": "06b8a06a", + "id": "7d4e3a22", "metadata": { "editable": true }, @@ -1538,7 +1538,7 @@ { "cell_type": "code", "execution_count": 9, - "id": "ccac70cc", + "id": "ebaa30a1", "metadata": { "collapsed": false, "editable": true @@ -1582,7 +1582,7 @@ }, { "cell_type": "markdown", - "id": "9df76aa4", + "id": "4814ac9f", "metadata": { "editable": true }, @@ -1605,7 +1605,7 @@ { "cell_type": "code", "execution_count": 10, - "id": "01e9c147", + "id": "6637dc3a", "metadata": { "collapsed": false, "editable": true @@ -1632,7 +1632,7 @@ }, { "cell_type": "markdown", - "id": "4c82978d", + "id": "6a6900f5", "metadata": { "editable": true }, @@ -1643,7 +1643,7 @@ { "cell_type": "code", "execution_count": 11, - "id": "2ed40e36", + "id": "a0f6228d", "metadata": { "collapsed": false, "editable": true @@ -1688,7 +1688,7 @@ }, { "cell_type": "markdown", - "id": "19d2a6e4", + "id": "44c09155", "metadata": { "editable": true }, @@ -1715,7 +1715,7 @@ }, { "cell_type": "markdown", - "id": "68ee067d", + "id": "77bd71a7", "metadata": { "editable": true }, @@ -1753,7 +1753,7 @@ }, { "cell_type": "markdown", - "id": "5a102ee5", + "id": "ce2fbb3d", "metadata": { "editable": true }, @@ -1765,7 +1765,7 @@ }, { "cell_type": "markdown", - "id": "0f1ca6e3", + "id": "879d5714", "metadata": { "editable": true }, @@ -1780,7 +1780,7 @@ }, { "cell_type": "markdown", - "id": "2d2f6865", + "id": "7745ce0e", "metadata": { "editable": true }, @@ -1790,7 +1790,7 @@ }, { "cell_type": "markdown", - "id": "90847299", + "id": "8b0d5a8a", "metadata": { "editable": true }, @@ -1803,7 +1803,7 @@ { "cell_type": "code", "execution_count": 12, - "id": "8a3f6f80", + "id": "5b55a578", "metadata": { "collapsed": false, "editable": true @@ -1879,7 +1879,7 @@ }, { "cell_type": "markdown", - "id": "2919417d", + "id": "d9c53340", "metadata": { "editable": true }, @@ -1889,7 +1889,7 @@ }, { "cell_type": "markdown", - "id": "e6331a72", + "id": "bac1dab3", "metadata": { "editable": true }, @@ -1900,7 +1900,7 @@ { "cell_type": "code", "execution_count": 13, - "id": "07203f4c", + "id": "beecbfc5", "metadata": { "collapsed": false, "editable": true @@ -1968,7 +1968,7 @@ }, { "cell_type": "markdown", - "id": "c3793883", + "id": "621fb11f", "metadata": { "editable": true }, @@ -1986,7 +1986,7 @@ }, { "cell_type": "markdown", - "id": "2c3af148", + "id": "719e5f7f", "metadata": { "editable": true }, @@ -2021,7 +2021,7 @@ { "cell_type": "code", "execution_count": 14, - "id": "da488fe6", + "id": "543cc574", "metadata": { "collapsed": false, "editable": true @@ -2033,7 +2033,7 @@ }, { "cell_type": "markdown", - "id": "70c8376f", + "id": "412729e1", "metadata": { "editable": true }, @@ -2045,7 +2045,7 @@ { "cell_type": "code", "execution_count": 15, - "id": "714f123f", + "id": "c5ec8938", "metadata": { "collapsed": false, "editable": true @@ -2058,7 +2058,7 @@ }, { "cell_type": "markdown", - "id": "c8773260", + "id": "9c6d6428", "metadata": { "editable": true }, @@ -2069,7 +2069,7 @@ { "cell_type": "code", "execution_count": 16, - "id": "903325d9", + "id": "54583091", "metadata": { "collapsed": false, "editable": true @@ -2082,7 +2082,7 @@ }, { "cell_type": "markdown", - "id": "d89fbd82", + "id": "a26c5a94", "metadata": { "editable": true }, @@ -2097,7 +2097,7 @@ { "cell_type": "code", "execution_count": 17, - "id": "ed3907b5", + "id": "258c4979", "metadata": { "collapsed": false, "editable": true @@ -2109,7 +2109,7 @@ }, { "cell_type": "markdown", - "id": "3e6104ca", + "id": "d5b6d9cd", "metadata": { "editable": true }, @@ -2121,7 +2121,7 @@ }, { "cell_type": "markdown", - "id": "d6fa3e46", + "id": "015ceead", "metadata": { "editable": true }, @@ -2134,7 +2134,7 @@ { "cell_type": "code", "execution_count": 18, - "id": "1fb10189", + "id": "150d32d9", "metadata": { "collapsed": false, "editable": true @@ -2189,7 +2189,7 @@ { "cell_type": "code", "execution_count": 19, - "id": "82050769", + "id": "65ff5321", "metadata": { "collapsed": false, "editable": true @@ -2218,7 +2218,7 @@ { "cell_type": "code", "execution_count": 20, - "id": "3045350b", + "id": "d53f312f", "metadata": { "collapsed": false, "editable": true @@ -2248,7 +2248,7 @@ { "cell_type": "code", "execution_count": 21, - "id": "4b60ee5e", + "id": "8ad38cb9", "metadata": { "collapsed": false, "editable": true @@ -2275,7 +2275,7 @@ { "cell_type": "code", "execution_count": 22, - "id": "2905ea58", + "id": "86db69c6", "metadata": { "collapsed": false, "editable": true @@ -2317,7 +2317,7 @@ }, { "cell_type": "markdown", - "id": "c8588356", + "id": "d8505aad", "metadata": { "editable": true }, @@ -2328,7 +2328,7 @@ { "cell_type": "code", "execution_count": 23, - "id": "7761ea42", + "id": "3e92f5a7", "metadata": { "collapsed": false, "editable": true @@ -2505,7 +2505,7 @@ }, { "cell_type": "markdown", - "id": "33ccb294", + "id": "6ee81bce", "metadata": { "editable": true }, @@ -2533,7 +2533,7 @@ }, { "cell_type": "markdown", - "id": "849eebaf", + "id": "dcbe8f77", "metadata": { "editable": true }, @@ -2556,7 +2556,7 @@ }, { "cell_type": "markdown", - "id": "c984843f", + "id": "a96fed60", "metadata": { "editable": true }, @@ -2587,7 +2587,7 @@ }, { "cell_type": "markdown", - "id": "74f3c2c9", + "id": "e4af9d16", "metadata": { "editable": true }, @@ -2619,7 +2619,7 @@ }, { "cell_type": "markdown", - "id": "a8f99adc", + "id": "28934494", "metadata": { "editable": true }, @@ -2657,7 +2657,7 @@ }, { "cell_type": "markdown", - "id": "c8deef7c", + "id": "4964c0d9", "metadata": { "editable": true }, @@ -2682,7 +2682,7 @@ }, { "cell_type": "markdown", - "id": "919c3e0c", + "id": "f8b4480c", "metadata": { "editable": true }, @@ -2694,7 +2694,7 @@ }, { "cell_type": "markdown", - "id": "c5a2fd72", + "id": "63f6fb19", "metadata": { "editable": true }, @@ -2717,7 +2717,7 @@ }, { "cell_type": "markdown", - "id": "59e96e5f", + "id": "6db7b6af", "metadata": { "editable": true }, @@ -2737,7 +2737,7 @@ }, { "cell_type": "markdown", - "id": "0a83cf59", + "id": "aa471ee5", "metadata": { "editable": true }, @@ -2759,7 +2759,7 @@ }, { "cell_type": "markdown", - "id": "695d6d51", + "id": "b6995145", "metadata": { "editable": true }, @@ -2777,7 +2777,7 @@ }, { "cell_type": "markdown", - "id": "bb92941f", + "id": "51f8d2f9", "metadata": { "editable": true }, @@ -2796,7 +2796,7 @@ }, { "cell_type": "markdown", - "id": "6d6d275c", + "id": "2d5a8be2", "metadata": { "editable": true }, @@ -2808,7 +2808,7 @@ }, { "cell_type": "markdown", - "id": "d920be3f", + "id": "2365782a", "metadata": { "editable": true }, @@ -2853,7 +2853,7 @@ }, { "cell_type": "markdown", - "id": "78805b82", + "id": "580cd291", "metadata": { "editable": true }, diff --git a/doc/pub/week42/html/._week42-bs000.html b/doc/pub/week42/html/._week42-bs000.html index 5012da2cf..6f608dbb9 100644 --- a/doc/pub/week42/html/._week42-bs000.html +++ b/doc/pub/week42/html/._week42-bs000.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • @@ -292,7 +292,7 @@ MathJax.Hub.Config({
    -

    Week 42

    +

    October 16-20, 2023


    diff --git a/doc/pub/week42/html/._week42-bs001.html b/doc/pub/week42/html/._week42-bs001.html index 9066f6c1d..1b3d4ceb5 100644 --- a/doc/pub/week42/html/._week42-bs001.html +++ b/doc/pub/week42/html/._week42-bs001.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs002.html b/doc/pub/week42/html/._week42-bs002.html index a072a86cb..7aafdfcd3 100644 --- a/doc/pub/week42/html/._week42-bs002.html +++ b/doc/pub/week42/html/._week42-bs002.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • @@ -274,7 +274,7 @@ MathJax.Hub.Config({

     

     

     

    -

    Lecture Thursday October 12

    +

    Lecture Thursday October 19

    diff --git a/doc/pub/week42/html/._week42-bs003.html b/doc/pub/week42/html/._week42-bs003.html index 76c3fdda2..31546de37 100644 --- a/doc/pub/week42/html/._week42-bs003.html +++ b/doc/pub/week42/html/._week42-bs003.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d

  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs004.html b/doc/pub/week42/html/._week42-bs004.html index 5cf4dc4f8..f03898fcb 100644 --- a/doc/pub/week42/html/._week42-bs004.html +++ b/doc/pub/week42/html/._week42-bs004.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs005.html b/doc/pub/week42/html/._week42-bs005.html index 8dccb46ba..c64ad9965 100644 --- a/doc/pub/week42/html/._week42-bs005.html +++ b/doc/pub/week42/html/._week42-bs005.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs006.html b/doc/pub/week42/html/._week42-bs006.html index a05b435fe..29e038501 100644 --- a/doc/pub/week42/html/._week42-bs006.html +++ b/doc/pub/week42/html/._week42-bs006.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs007.html b/doc/pub/week42/html/._week42-bs007.html index 1d4a5c693..3701ddf6f 100644 --- a/doc/pub/week42/html/._week42-bs007.html +++ b/doc/pub/week42/html/._week42-bs007.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs008.html b/doc/pub/week42/html/._week42-bs008.html index 91403dc5e..6f2cd0b5c 100644 --- a/doc/pub/week42/html/._week42-bs008.html +++ b/doc/pub/week42/html/._week42-bs008.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs009.html b/doc/pub/week42/html/._week42-bs009.html index 6df60b711..67bdc21b1 100644 --- a/doc/pub/week42/html/._week42-bs009.html +++ b/doc/pub/week42/html/._week42-bs009.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs010.html b/doc/pub/week42/html/._week42-bs010.html index 32d39f638..eb75a94f3 100644 --- a/doc/pub/week42/html/._week42-bs010.html +++ b/doc/pub/week42/html/._week42-bs010.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs011.html b/doc/pub/week42/html/._week42-bs011.html index 21e6db2b0..27d2fb0a9 100644 --- a/doc/pub/week42/html/._week42-bs011.html +++ b/doc/pub/week42/html/._week42-bs011.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs012.html b/doc/pub/week42/html/._week42-bs012.html index 1d73ca3ec..98831a986 100644 --- a/doc/pub/week42/html/._week42-bs012.html +++ b/doc/pub/week42/html/._week42-bs012.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs013.html b/doc/pub/week42/html/._week42-bs013.html index 0efa8a6f9..73976be35 100644 --- a/doc/pub/week42/html/._week42-bs013.html +++ b/doc/pub/week42/html/._week42-bs013.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs014.html b/doc/pub/week42/html/._week42-bs014.html index 5933196b3..6466d8eb7 100644 --- a/doc/pub/week42/html/._week42-bs014.html +++ b/doc/pub/week42/html/._week42-bs014.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs015.html b/doc/pub/week42/html/._week42-bs015.html index 3481e952d..742186e7b 100644 --- a/doc/pub/week42/html/._week42-bs015.html +++ b/doc/pub/week42/html/._week42-bs015.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs016.html b/doc/pub/week42/html/._week42-bs016.html index ea9520ebb..e1d266325 100644 --- a/doc/pub/week42/html/._week42-bs016.html +++ b/doc/pub/week42/html/._week42-bs016.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs017.html b/doc/pub/week42/html/._week42-bs017.html index cc3c82a35..a11a09781 100644 --- a/doc/pub/week42/html/._week42-bs017.html +++ b/doc/pub/week42/html/._week42-bs017.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs018.html b/doc/pub/week42/html/._week42-bs018.html index 2f08c7e3f..9a88b902b 100644 --- a/doc/pub/week42/html/._week42-bs018.html +++ b/doc/pub/week42/html/._week42-bs018.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs019.html b/doc/pub/week42/html/._week42-bs019.html index cdc463f60..a1fbcb8dc 100644 --- a/doc/pub/week42/html/._week42-bs019.html +++ b/doc/pub/week42/html/._week42-bs019.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs020.html b/doc/pub/week42/html/._week42-bs020.html index 899120548..a2ca09f71 100644 --- a/doc/pub/week42/html/._week42-bs020.html +++ b/doc/pub/week42/html/._week42-bs020.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs021.html b/doc/pub/week42/html/._week42-bs021.html index 5e6e1779d..a43e96c64 100644 --- a/doc/pub/week42/html/._week42-bs021.html +++ b/doc/pub/week42/html/._week42-bs021.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs022.html b/doc/pub/week42/html/._week42-bs022.html index ee67013c7..d3eb3e24b 100644 --- a/doc/pub/week42/html/._week42-bs022.html +++ b/doc/pub/week42/html/._week42-bs022.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs023.html b/doc/pub/week42/html/._week42-bs023.html index f496cac9d..24d1e9e86 100644 --- a/doc/pub/week42/html/._week42-bs023.html +++ b/doc/pub/week42/html/._week42-bs023.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs024.html b/doc/pub/week42/html/._week42-bs024.html index 5fb1d6a48..4fef2f395 100644 --- a/doc/pub/week42/html/._week42-bs024.html +++ b/doc/pub/week42/html/._week42-bs024.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs025.html b/doc/pub/week42/html/._week42-bs025.html index 82c745ef9..726c78def 100644 --- a/doc/pub/week42/html/._week42-bs025.html +++ b/doc/pub/week42/html/._week42-bs025.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs026.html b/doc/pub/week42/html/._week42-bs026.html index 7645e744b..382da3519 100644 --- a/doc/pub/week42/html/._week42-bs026.html +++ b/doc/pub/week42/html/._week42-bs026.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs027.html b/doc/pub/week42/html/._week42-bs027.html index 0022eec9e..99611235f 100644 --- a/doc/pub/week42/html/._week42-bs027.html +++ b/doc/pub/week42/html/._week42-bs027.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs028.html b/doc/pub/week42/html/._week42-bs028.html index 51625d63f..141a92b43 100644 --- a/doc/pub/week42/html/._week42-bs028.html +++ b/doc/pub/week42/html/._week42-bs028.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs029.html b/doc/pub/week42/html/._week42-bs029.html index d4ecb2c23..cc1903be2 100644 --- a/doc/pub/week42/html/._week42-bs029.html +++ b/doc/pub/week42/html/._week42-bs029.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs030.html b/doc/pub/week42/html/._week42-bs030.html index 409f71e06..a83a31359 100644 --- a/doc/pub/week42/html/._week42-bs030.html +++ b/doc/pub/week42/html/._week42-bs030.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs031.html b/doc/pub/week42/html/._week42-bs031.html index 06d3ed116..56e8f51b5 100644 --- a/doc/pub/week42/html/._week42-bs031.html +++ b/doc/pub/week42/html/._week42-bs031.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs032.html b/doc/pub/week42/html/._week42-bs032.html index 87fb4c1a1..414500b5f 100644 --- a/doc/pub/week42/html/._week42-bs032.html +++ b/doc/pub/week42/html/._week42-bs032.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs033.html b/doc/pub/week42/html/._week42-bs033.html index ab83ded05..38d136454 100644 --- a/doc/pub/week42/html/._week42-bs033.html +++ b/doc/pub/week42/html/._week42-bs033.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs034.html b/doc/pub/week42/html/._week42-bs034.html index b2e561356..1380ea18a 100644 --- a/doc/pub/week42/html/._week42-bs034.html +++ b/doc/pub/week42/html/._week42-bs034.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs035.html b/doc/pub/week42/html/._week42-bs035.html index cf2c061ce..56c8c5d25 100644 --- a/doc/pub/week42/html/._week42-bs035.html +++ b/doc/pub/week42/html/._week42-bs035.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs036.html b/doc/pub/week42/html/._week42-bs036.html index 7e3c47e5c..9580cd973 100644 --- a/doc/pub/week42/html/._week42-bs036.html +++ b/doc/pub/week42/html/._week42-bs036.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs037.html b/doc/pub/week42/html/._week42-bs037.html index 8dd35ff4b..4ce8cf603 100644 --- a/doc/pub/week42/html/._week42-bs037.html +++ b/doc/pub/week42/html/._week42-bs037.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs038.html b/doc/pub/week42/html/._week42-bs038.html index c9462ddee..142e5b658 100644 --- a/doc/pub/week42/html/._week42-bs038.html +++ b/doc/pub/week42/html/._week42-bs038.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs039.html b/doc/pub/week42/html/._week42-bs039.html index 9bebbd998..6c7852e30 100644 --- a/doc/pub/week42/html/._week42-bs039.html +++ b/doc/pub/week42/html/._week42-bs039.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs040.html b/doc/pub/week42/html/._week42-bs040.html index 5e7d1d96f..64935863d 100644 --- a/doc/pub/week42/html/._week42-bs040.html +++ b/doc/pub/week42/html/._week42-bs040.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs041.html b/doc/pub/week42/html/._week42-bs041.html index 22567958f..8f3ab0cb4 100644 --- a/doc/pub/week42/html/._week42-bs041.html +++ b/doc/pub/week42/html/._week42-bs041.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs042.html b/doc/pub/week42/html/._week42-bs042.html index 597ac3a48..35e300c51 100644 --- a/doc/pub/week42/html/._week42-bs042.html +++ b/doc/pub/week42/html/._week42-bs042.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs043.html b/doc/pub/week42/html/._week42-bs043.html index 936286585..49a1c195b 100644 --- a/doc/pub/week42/html/._week42-bs043.html +++ b/doc/pub/week42/html/._week42-bs043.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs044.html b/doc/pub/week42/html/._week42-bs044.html index 034d98b14..90b862a43 100644 --- a/doc/pub/week42/html/._week42-bs044.html +++ b/doc/pub/week42/html/._week42-bs044.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs045.html b/doc/pub/week42/html/._week42-bs045.html index 01e3238fd..215312369 100644 --- a/doc/pub/week42/html/._week42-bs045.html +++ b/doc/pub/week42/html/._week42-bs045.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs046.html b/doc/pub/week42/html/._week42-bs046.html index bc56d0ba9..8685170a9 100644 --- a/doc/pub/week42/html/._week42-bs046.html +++ b/doc/pub/week42/html/._week42-bs046.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs047.html b/doc/pub/week42/html/._week42-bs047.html index 559e29eeb..3b7e7d750 100644 --- a/doc/pub/week42/html/._week42-bs047.html +++ b/doc/pub/week42/html/._week42-bs047.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs048.html b/doc/pub/week42/html/._week42-bs048.html index a508a10ba..d317cdc4f 100644 --- a/doc/pub/week42/html/._week42-bs048.html +++ b/doc/pub/week42/html/._week42-bs048.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs049.html b/doc/pub/week42/html/._week42-bs049.html index 78de33e8c..1bc507172 100644 --- a/doc/pub/week42/html/._week42-bs049.html +++ b/doc/pub/week42/html/._week42-bs049.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs050.html b/doc/pub/week42/html/._week42-bs050.html index 0a365740f..1e17d2938 100644 --- a/doc/pub/week42/html/._week42-bs050.html +++ b/doc/pub/week42/html/._week42-bs050.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/._week42-bs051.html b/doc/pub/week42/html/._week42-bs051.html index 6aa3c24de..f0171e987 100644 --- a/doc/pub/week42/html/._week42-bs051.html +++ b/doc/pub/week42/html/._week42-bs051.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • diff --git a/doc/pub/week42/html/week42-bs.html b/doc/pub/week42/html/week42-bs.html index 5012da2cf..6f608dbb9 100644 --- a/doc/pub/week42/html/week42-bs.html +++ b/doc/pub/week42/html/week42-bs.html @@ -37,10 +37,10 @@ doconce format html week42.do.txt --html_style=bootstrap --pygments_html_style=d
  • Plan for week 42
    • -
  • Lecture Thursday October 12
    • +
  • Lecture Thursday October 19
  • Review of the back propagation algorithm
  • Setting up the Back propagation algorithm
  • Setting up a Multi-layer perceptron model for classification
    • @@ -292,7 +292,7 @@ MathJax.Hub.Config({
    -

    Week 42

    +

    October 16-20, 2023


    diff --git a/doc/pub/week42/html/week42-reveal.html b/doc/pub/week42/html/week42-reveal.html index a0a3d7beb..eb63767fb 100644 --- a/doc/pub/week42/html/week42-reveal.html +++ b/doc/pub/week42/html/week42-reveal.html @@ -184,7 +184,7 @@ MathJax.Hub.Config({
    -

    Week 42

    +

    October 16-20, 2023


    @@ -243,7 +243,7 @@ MathJax.Hub.Config({
    -

    Lecture Thursday October 12

    +

    Lecture Thursday October 19

    diff --git a/doc/pub/week42/html/week42-solarized.html b/doc/pub/week42/html/week42-solarized.html index 50fa4de84..35551489d 100644 --- a/doc/pub/week42/html/week42-solarized.html +++ b/doc/pub/week42/html/week42-solarized.html @@ -64,10 +64,10 @@ div.toc p,a {
    @@ -281,7 +281,7 @@ MathJax.Hub.Config({









    -

    Lecture Thursday October 12

    +

    Lecture Thursday October 19











    Review of the back propagation algorithm

    diff --git a/doc/pub/week42/html/week42.html b/doc/pub/week42/html/week42.html index 3bbba9c6d..5f5ea50f5 100644 --- a/doc/pub/week42/html/week42.html +++ b/doc/pub/week42/html/week42.html @@ -141,10 +141,10 @@ div.toc p,a {
    @@ -358,7 +358,7 @@ MathJax.Hub.Config({









    -

    Lecture Thursday October 12

    +

    Lecture Thursday October 19











    Review of the back propagation algorithm

    diff --git a/doc/pub/week42/ipynb/ipynb-week42-src.tar.gz b/doc/pub/week42/ipynb/ipynb-week42-src.tar.gz index 18a520757..bc0d9d974 100644 Binary files a/doc/pub/week42/ipynb/ipynb-week42-src.tar.gz and b/doc/pub/week42/ipynb/ipynb-week42-src.tar.gz differ diff --git a/doc/pub/week42/ipynb/week42.ipynb b/doc/pub/week42/ipynb/week42.ipynb index a55b73018..adc0b59eb 100644 --- a/doc/pub/week42/ipynb/week42.ipynb +++ b/doc/pub/week42/ipynb/week42.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "markdown", - "id": "6f748484", + "id": "d2a36f3c", "metadata": { "editable": true }, @@ -14,7 +14,7 @@ }, { "cell_type": "markdown", - "id": "a2333337", + "id": "310c269f", "metadata": { "editable": true }, @@ -22,12 +22,12 @@ "# Week 42 Constructing a Neural Network code with introduction to Tensor flow\n", "**Morten Hjorth-Jensen**, Department of Physics, University of Oslo and Department of Physics and Astronomy and Facility for Rare Isotope Beams, Michigan State University\n", "\n", - "Date: **Week 42**" + "Date: **October 16-20, 2023**" ] }, { "cell_type": "markdown", - "id": "0afbab80", + "id": "427a552f", "metadata": { "editable": true }, @@ -69,17 +69,17 @@ }, { "cell_type": "markdown", - "id": "218979dd", + "id": "b53157af", "metadata": { "editable": true }, "source": [ - "## Lecture Thursday October 12" + "## Lecture Thursday October 19" ] }, { "cell_type": "markdown", - "id": "0bc89100", + "id": "9002bf39", "metadata": { "editable": true }, @@ -94,7 +94,7 @@ }, { "cell_type": "markdown", - "id": "878894aa", + "id": "228a98c1", "metadata": { "editable": true }, @@ -117,7 +117,7 @@ }, { "cell_type": "markdown", - "id": "77f6818e", + "id": "c38b5eaf", "metadata": { "editable": true }, @@ -129,7 +129,7 @@ }, { "cell_type": "markdown", - "id": "44a6eb1e", + "id": "991e9164", "metadata": { "editable": true }, @@ -139,7 +139,7 @@ }, { "cell_type": "markdown", - "id": "bde0c34a", + "id": "b5c5f27f", "metadata": { "editable": true }, @@ -151,7 +151,7 @@ }, { "cell_type": "markdown", - "id": "95ad0241", + "id": "41dd527c", "metadata": { "editable": true }, @@ -161,7 +161,7 @@ }, { "cell_type": "markdown", - "id": "9487e01a", + "id": "49fa0a94", "metadata": { "editable": true }, @@ -173,7 +173,7 @@ }, { "cell_type": "markdown", - "id": "2763e7bc", + "id": "da9bdf96", "metadata": { "editable": true }, @@ -185,7 +185,7 @@ }, { "cell_type": "markdown", - "id": "c4ba4400", + "id": "7e012a3c", "metadata": { "editable": true }, @@ -196,7 +196,7 @@ }, { "cell_type": "markdown", - "id": "4623a430", + "id": "a10b5095", "metadata": { "editable": true }, @@ -224,7 +224,7 @@ }, { "cell_type": "markdown", - "id": "73be143c", + "id": "dae5d47e", "metadata": { "editable": true }, @@ -236,7 +236,7 @@ }, { "cell_type": "markdown", - "id": "88b61ced", + "id": "2b98a58c", "metadata": { "editable": true }, @@ -246,7 +246,7 @@ }, { "cell_type": "markdown", - "id": "36e7d5b4", + "id": "d44d09a5", "metadata": { "editable": true }, @@ -258,7 +258,7 @@ }, { "cell_type": "markdown", - "id": "2132d8d9", + "id": "deac74cc", "metadata": { "editable": true }, @@ -269,7 +269,7 @@ }, { "cell_type": "markdown", - "id": "e73b584a", + "id": "9346792f", "metadata": { "editable": true }, @@ -281,7 +281,7 @@ }, { "cell_type": "markdown", - "id": "ead64ff0", + "id": "cd47740a", "metadata": { "editable": true }, @@ -294,7 +294,7 @@ }, { "cell_type": "markdown", - "id": "175865ba", + "id": "624d266a", "metadata": { "editable": true }, @@ -319,7 +319,7 @@ }, { "cell_type": "markdown", - "id": "8ff83c23", + "id": "ab1fdd1f", "metadata": { "editable": true }, @@ -332,7 +332,7 @@ }, { "cell_type": "markdown", - "id": "e4e3e3ae", + "id": "a005eeef", "metadata": { "editable": true }, @@ -344,7 +344,7 @@ }, { "cell_type": "markdown", - "id": "9bb50a82", + "id": "0d9e3087", "metadata": { "editable": true }, @@ -356,7 +356,7 @@ }, { "cell_type": "markdown", - "id": "0df7623e", + "id": "308b820e", "metadata": { "editable": true }, @@ -366,7 +366,7 @@ }, { "cell_type": "markdown", - "id": "007c5ccb", + "id": "ae243251", "metadata": { "editable": true }, @@ -378,7 +378,7 @@ }, { "cell_type": "markdown", - "id": "46517787", + "id": "79055e74", "metadata": { "editable": true }, @@ -390,7 +390,7 @@ }, { "cell_type": "markdown", - "id": "2e5272ee", + "id": "fa673507", "metadata": { "editable": true }, @@ -402,7 +402,7 @@ }, { "cell_type": "markdown", - "id": "c4c9df05", + "id": "4cc3f2e2", "metadata": { "editable": true }, @@ -414,7 +414,7 @@ }, { "cell_type": "markdown", - "id": "f31ae9bc", + "id": "28883e22", "metadata": { "editable": true }, @@ -424,7 +424,7 @@ }, { "cell_type": "markdown", - "id": "c0f2db30", + "id": "c2563a79", "metadata": { "editable": true }, @@ -436,7 +436,7 @@ }, { "cell_type": "markdown", - "id": "b0a4e033", + "id": "f267068b", "metadata": { "editable": true }, @@ -446,7 +446,7 @@ }, { "cell_type": "markdown", - "id": "c6d9a957", + "id": "8a4a0387", "metadata": { "editable": true }, @@ -458,7 +458,7 @@ }, { "cell_type": "markdown", - "id": "6a2015ea", + "id": "19fb027a", "metadata": { "editable": true }, @@ -471,7 +471,7 @@ }, { "cell_type": "markdown", - "id": "9095b828", + "id": "f41bc98e", "metadata": { "editable": true }, @@ -483,7 +483,7 @@ }, { "cell_type": "markdown", - "id": "3fcc73a0", + "id": "23638b6a", "metadata": { "editable": true }, @@ -493,7 +493,7 @@ }, { "cell_type": "markdown", - "id": "0a29ae09", + "id": "d3f6e3e3", "metadata": { "editable": true }, @@ -505,7 +505,7 @@ }, { "cell_type": "markdown", - "id": "98d33296", + "id": "61c4f101", "metadata": { "editable": true }, @@ -516,7 +516,7 @@ }, { "cell_type": "markdown", - "id": "429ed394", + "id": "58ac0397", "metadata": { "editable": true }, @@ -528,7 +528,7 @@ }, { "cell_type": "markdown", - "id": "2a5136a4", + "id": "585c0850", "metadata": { "editable": true }, @@ -538,7 +538,7 @@ }, { "cell_type": "markdown", - "id": "192baba3", + "id": "f6b1c1c8", "metadata": { "editable": true }, @@ -550,7 +550,7 @@ }, { "cell_type": "markdown", - "id": "31947c1f", + "id": "97ae8668", "metadata": { "editable": true }, @@ -560,7 +560,7 @@ }, { "cell_type": "markdown", - "id": "ccabb47b", + "id": "28f524e4", "metadata": { "editable": true }, @@ -571,7 +571,7 @@ }, { "cell_type": "markdown", - "id": "637e9a4f", + "id": "233b736f", "metadata": { "editable": true }, @@ -584,7 +584,7 @@ }, { "cell_type": "markdown", - "id": "72777fcb", + "id": "f0e7c038", "metadata": { "editable": true }, @@ -594,7 +594,7 @@ }, { "cell_type": "markdown", - "id": "acae325f", + "id": "d17816a2", "metadata": { "editable": true }, @@ -606,7 +606,7 @@ }, { "cell_type": "markdown", - "id": "4e52aa77", + "id": "1a196a75", "metadata": { "editable": true }, @@ -616,7 +616,7 @@ }, { "cell_type": "markdown", - "id": "14ede160", + "id": "b2dcca96", "metadata": { "editable": true }, @@ -628,7 +628,7 @@ }, { "cell_type": "markdown", - "id": "8eed9d34", + "id": "1f8acea2", "metadata": { "editable": true }, @@ -638,7 +638,7 @@ }, { "cell_type": "markdown", - "id": "ad7bcdbc", + "id": "4adc4dc7", "metadata": { "editable": true }, @@ -662,7 +662,7 @@ }, { "cell_type": "markdown", - "id": "c6a34b9d", + "id": "17f30edb", "metadata": { "editable": true }, @@ -712,7 +712,7 @@ { "cell_type": "code", "execution_count": 1, - "id": "98bdaf7c", + "id": "69ec827f", "metadata": { "collapsed": false, "editable": true @@ -767,7 +767,7 @@ }, { "cell_type": "markdown", - "id": "ee64810c", + "id": "867080d1", "metadata": { "editable": true }, @@ -788,7 +788,7 @@ { "cell_type": "code", "execution_count": 2, - "id": "09b3024d", + "id": "1659b538", "metadata": { "collapsed": false, "editable": true @@ -826,7 +826,7 @@ }, { "cell_type": "markdown", - "id": "17382aef", + "id": "304e16d9", "metadata": { "editable": true }, @@ -870,7 +870,7 @@ }, { "cell_type": "markdown", - "id": "1f8a5a07", + "id": "73aaf166", "metadata": { "editable": true }, @@ -910,7 +910,7 @@ }, { "cell_type": "markdown", - "id": "679bc5ef", + "id": "302a43c9", "metadata": { "editable": true }, @@ -931,7 +931,7 @@ { "cell_type": "code", "execution_count": 3, - "id": "31947cdb", + "id": "20c961e1", "metadata": { "collapsed": false, "editable": true @@ -957,7 +957,7 @@ }, { "cell_type": "markdown", - "id": "10bf669a", + "id": "b63a63bc", "metadata": { "editable": true }, @@ -985,7 +985,7 @@ }, { "cell_type": "markdown", - "id": "4f812b1d", + "id": "a1ee6c2a", "metadata": { "editable": true }, @@ -1022,7 +1022,7 @@ { "cell_type": "code", "execution_count": 4, - "id": "c7f08a08", + "id": "85e741aa", "metadata": { "collapsed": false, "editable": true @@ -1068,7 +1068,7 @@ }, { "cell_type": "markdown", - "id": "51211bf4", + "id": "618d4858", "metadata": { "editable": true }, @@ -1099,7 +1099,7 @@ }, { "cell_type": "markdown", - "id": "0c28bf7b", + "id": "7c098021", "metadata": { "editable": true }, @@ -1137,7 +1137,7 @@ }, { "cell_type": "markdown", - "id": "0357f19f", + "id": "bcfe9ca6", "metadata": { "editable": true }, @@ -1171,7 +1171,7 @@ }, { "cell_type": "markdown", - "id": "c45865cf", + "id": "be9470b3", "metadata": { "editable": true }, @@ -1212,7 +1212,7 @@ { "cell_type": "code", "execution_count": 5, - "id": "e0641df5", + "id": "3b549560", "metadata": { "collapsed": false, "editable": true @@ -1291,7 +1291,7 @@ }, { "cell_type": "markdown", - "id": "feebbdcb", + "id": "70834cc0", "metadata": { "editable": true }, @@ -1312,7 +1312,7 @@ }, { "cell_type": "markdown", - "id": "a9fce5a7", + "id": "feb328ab", "metadata": { "editable": true }, @@ -1326,7 +1326,7 @@ { "cell_type": "code", "execution_count": 6, - "id": "88ce9dfc", + "id": "bd075104", "metadata": { "collapsed": false, "editable": true @@ -1436,7 +1436,7 @@ }, { "cell_type": "markdown", - "id": "e9abf91b", + "id": "0b719fba", "metadata": { "editable": true }, @@ -1455,7 +1455,7 @@ { "cell_type": "code", "execution_count": 7, - "id": "841bda7c", + "id": "78fbbfb2", "metadata": { "collapsed": false, "editable": true @@ -1482,7 +1482,7 @@ }, { "cell_type": "markdown", - "id": "6bb4719d", + "id": "bcce4264", "metadata": { "editable": true }, @@ -1496,7 +1496,7 @@ { "cell_type": "code", "execution_count": 8, - "id": "3d940b93", + "id": "a8928377", "metadata": { "collapsed": false, "editable": true @@ -1527,7 +1527,7 @@ }, { "cell_type": "markdown", - "id": "06b8a06a", + "id": "7d4e3a22", "metadata": { "editable": true }, @@ -1538,7 +1538,7 @@ { "cell_type": "code", "execution_count": 9, - "id": "ccac70cc", + "id": "ebaa30a1", "metadata": { "collapsed": false, "editable": true @@ -1582,7 +1582,7 @@ }, { "cell_type": "markdown", - "id": "9df76aa4", + "id": "4814ac9f", "metadata": { "editable": true }, @@ -1605,7 +1605,7 @@ { "cell_type": "code", "execution_count": 10, - "id": "01e9c147", + "id": "6637dc3a", "metadata": { "collapsed": false, "editable": true @@ -1632,7 +1632,7 @@ }, { "cell_type": "markdown", - "id": "4c82978d", + "id": "6a6900f5", "metadata": { "editable": true }, @@ -1643,7 +1643,7 @@ { "cell_type": "code", "execution_count": 11, - "id": "2ed40e36", + "id": "a0f6228d", "metadata": { "collapsed": false, "editable": true @@ -1688,7 +1688,7 @@ }, { "cell_type": "markdown", - "id": "19d2a6e4", + "id": "44c09155", "metadata": { "editable": true }, @@ -1715,7 +1715,7 @@ }, { "cell_type": "markdown", - "id": "68ee067d", + "id": "77bd71a7", "metadata": { "editable": true }, @@ -1753,7 +1753,7 @@ }, { "cell_type": "markdown", - "id": "5a102ee5", + "id": "ce2fbb3d", "metadata": { "editable": true }, @@ -1765,7 +1765,7 @@ }, { "cell_type": "markdown", - "id": "0f1ca6e3", + "id": "879d5714", "metadata": { "editable": true }, @@ -1780,7 +1780,7 @@ }, { "cell_type": "markdown", - "id": "2d2f6865", + "id": "7745ce0e", "metadata": { "editable": true }, @@ -1790,7 +1790,7 @@ }, { "cell_type": "markdown", - "id": "90847299", + "id": "8b0d5a8a", "metadata": { "editable": true }, @@ -1803,7 +1803,7 @@ { "cell_type": "code", "execution_count": 12, - "id": "8a3f6f80", + "id": "5b55a578", "metadata": { "collapsed": false, "editable": true @@ -1879,7 +1879,7 @@ }, { "cell_type": "markdown", - "id": "2919417d", + "id": "d9c53340", "metadata": { "editable": true }, @@ -1889,7 +1889,7 @@ }, { "cell_type": "markdown", - "id": "e6331a72", + "id": "bac1dab3", "metadata": { "editable": true }, @@ -1900,7 +1900,7 @@ { "cell_type": "code", "execution_count": 13, - "id": "07203f4c", + "id": "beecbfc5", "metadata": { "collapsed": false, "editable": true @@ -1968,7 +1968,7 @@ }, { "cell_type": "markdown", - "id": "c3793883", + "id": "621fb11f", "metadata": { "editable": true }, @@ -1986,7 +1986,7 @@ }, { "cell_type": "markdown", - "id": "2c3af148", + "id": "719e5f7f", "metadata": { "editable": true }, @@ -2021,7 +2021,7 @@ { "cell_type": "code", "execution_count": 14, - "id": "da488fe6", + "id": "543cc574", "metadata": { "collapsed": false, "editable": true @@ -2033,7 +2033,7 @@ }, { "cell_type": "markdown", - "id": "70c8376f", + "id": "412729e1", "metadata": { "editable": true }, @@ -2045,7 +2045,7 @@ { "cell_type": "code", "execution_count": 15, - "id": "714f123f", + "id": "c5ec8938", "metadata": { "collapsed": false, "editable": true @@ -2058,7 +2058,7 @@ }, { "cell_type": "markdown", - "id": "c8773260", + "id": "9c6d6428", "metadata": { "editable": true }, @@ -2069,7 +2069,7 @@ { "cell_type": "code", "execution_count": 16, - "id": "903325d9", + "id": "54583091", "metadata": { "collapsed": false, "editable": true @@ -2082,7 +2082,7 @@ }, { "cell_type": "markdown", - "id": "d89fbd82", + "id": "a26c5a94", "metadata": { "editable": true }, @@ -2097,7 +2097,7 @@ { "cell_type": "code", "execution_count": 17, - "id": "ed3907b5", + "id": "258c4979", "metadata": { "collapsed": false, "editable": true @@ -2109,7 +2109,7 @@ }, { "cell_type": "markdown", - "id": "3e6104ca", + "id": "d5b6d9cd", "metadata": { "editable": true }, @@ -2121,7 +2121,7 @@ }, { "cell_type": "markdown", - "id": "d6fa3e46", + "id": "015ceead", "metadata": { "editable": true }, @@ -2134,7 +2134,7 @@ { "cell_type": "code", "execution_count": 18, - "id": "1fb10189", + "id": "150d32d9", "metadata": { "collapsed": false, "editable": true @@ -2189,7 +2189,7 @@ { "cell_type": "code", "execution_count": 19, - "id": "82050769", + "id": "65ff5321", "metadata": { "collapsed": false, "editable": true @@ -2218,7 +2218,7 @@ { "cell_type": "code", "execution_count": 20, - "id": "3045350b", + "id": "d53f312f", "metadata": { "collapsed": false, "editable": true @@ -2248,7 +2248,7 @@ { "cell_type": "code", "execution_count": 21, - "id": "4b60ee5e", + "id": "8ad38cb9", "metadata": { "collapsed": false, "editable": true @@ -2275,7 +2275,7 @@ { "cell_type": "code", "execution_count": 22, - "id": "2905ea58", + "id": "86db69c6", "metadata": { "collapsed": false, "editable": true @@ -2317,7 +2317,7 @@ }, { "cell_type": "markdown", - "id": "c8588356", + "id": "d8505aad", "metadata": { "editable": true }, @@ -2328,7 +2328,7 @@ { "cell_type": "code", "execution_count": 23, - "id": "7761ea42", + "id": "3e92f5a7", "metadata": { "collapsed": false, "editable": true @@ -2505,7 +2505,7 @@ }, { "cell_type": "markdown", - "id": "33ccb294", + "id": "6ee81bce", "metadata": { "editable": true }, @@ -2533,7 +2533,7 @@ }, { "cell_type": "markdown", - "id": "849eebaf", + "id": "dcbe8f77", "metadata": { "editable": true }, @@ -2556,7 +2556,7 @@ }, { "cell_type": "markdown", - "id": "c984843f", + "id": "a96fed60", "metadata": { "editable": true }, @@ -2587,7 +2587,7 @@ }, { "cell_type": "markdown", - "id": "74f3c2c9", + "id": "e4af9d16", "metadata": { "editable": true }, @@ -2619,7 +2619,7 @@ }, { "cell_type": "markdown", - "id": "a8f99adc", + "id": "28934494", "metadata": { "editable": true }, @@ -2657,7 +2657,7 @@ }, { "cell_type": "markdown", - "id": "c8deef7c", + "id": "4964c0d9", "metadata": { "editable": true }, @@ -2682,7 +2682,7 @@ }, { "cell_type": "markdown", - "id": "919c3e0c", + "id": "f8b4480c", "metadata": { "editable": true }, @@ -2694,7 +2694,7 @@ }, { "cell_type": "markdown", - "id": "c5a2fd72", + "id": "63f6fb19", "metadata": { "editable": true }, @@ -2717,7 +2717,7 @@ }, { "cell_type": "markdown", - "id": "59e96e5f", + "id": "6db7b6af", "metadata": { "editable": true }, @@ -2737,7 +2737,7 @@ }, { "cell_type": "markdown", - "id": "0a83cf59", + "id": "aa471ee5", "metadata": { "editable": true }, @@ -2759,7 +2759,7 @@ }, { "cell_type": "markdown", - "id": "695d6d51", + "id": "b6995145", "metadata": { "editable": true }, @@ -2777,7 +2777,7 @@ }, { "cell_type": "markdown", - "id": "bb92941f", + "id": "51f8d2f9", "metadata": { "editable": true }, @@ -2796,7 +2796,7 @@ }, { "cell_type": "markdown", - "id": "6d6d275c", + "id": "2d5a8be2", "metadata": { "editable": true }, @@ -2808,7 +2808,7 @@ }, { "cell_type": "markdown", - "id": "d920be3f", + "id": "2365782a", "metadata": { "editable": true }, @@ -2853,7 +2853,7 @@ }, { "cell_type": "markdown", - "id": "78805b82", + "id": "580cd291", "metadata": { "editable": true }, diff --git a/doc/src/week42/exercisesweek42.ipynb b/doc/src/week42/exercisesweek42.ipynb deleted file mode 100644 index f64e52145..000000000 --- a/doc/src/week42/exercisesweek42.ipynb +++ /dev/null @@ -1,73 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "id": "be117070", - "metadata": { - "editable": true - }, - "source": [ - "\n", - "" - ] - }, - { - "cell_type": "markdown", - "id": "6f7356c3", - "metadata": { - "editable": true - }, - "source": [ - "# Exercises week 42\n", - "**October 9-13, 2023**\n", - "\n", - "Date: **Deadline is Sunday October 22 at midnight**\n", - "\n", - "You can hand in the exercises from week 41 and week 42 as one exercise and get a total score of two additional points." - ] - }, - { - "cell_type": "markdown", - "id": "aa378ef2", - "metadata": { - "editable": true - }, - "source": [ - "# Overarching aims of the exercises this week\n", - "\n", - "The aim of the exercises this week is to get started with implementing\n", - "gradient methods of relevance for project 2. The exercise this week is a simple\n", - "continuation from the previous week with the addition of automatic differentation.\n", - "Everything you develop here will be used in project 2. \n", - "\n", - "In order to get started, we will now replace in our standard ordinary\n", - "least squares (OLS) and Ridge regression codes (from project 1) the\n", - "matrix inversion algorithm with our own gradient descent (GD) and SGD\n", - "codes. You can use the Franke function or the terrain data from\n", - "project 1. **However, we recommend using a simpler function like**\n", - "$f(x)=a_0+a_1x+a_2x^2$ or higher-order one-dimensional polynomials.\n", - "You can obviously test your final codes against for example the Franke\n", - "function. Automatic differentiation will be discussed next week.\n", - "\n", - "You should include in your analysis of the GD and SGD codes the following elements\n", - "1. A plain gradient descent with a fixed learning rate (you will need to tune it) using automatic differentiation. Compare this with the analytical expression of the gradients you obtained last week. Feel free to use **Autograd** as Python package or **JAX**. You can use the examples form last week.\n", - "\n", - "2. Add momentum to the plain GD code and compare convergence with a fixed learning rate (you may need to tune the learning rate). Compare this with the analytical expression of the gradients you obtained last week.\n", - "\n", - "3. Repeat these steps for stochastic gradient descent with mini batches and a given number of epochs. Use a tunable learning rate as discussed in the lectures from week 39. Discuss the results as functions of the various parameters (size of batches, number of epochs etc)\n", - "\n", - "4. Implement the Adagrad method in order to tune the learning rate. Do this with and without momentum for plain gradient descent and SGD using automatic differentiation..\n", - "\n", - "5. Add RMSprop and Adam to your library of methods for tuning the learning rate. Again using automatic differentiation.\n", - "\n", - "The lecture notes from weeks 39 and 40 contain more information and code examples. Feel free to use these examples.\n", - "\n", - "We recommend reading chapter 8 on optimization from the textbook of [Goodfellow, Bengio and Courville](https://www.deeplearningbook.org/). This chapter contains many useful insights and discussions on the optimization part of machine learning." - ] - } - ], - "metadata": {}, - "nbformat": 4, - "nbformat_minor": 5 -} diff --git a/doc/src/week42/week42.do.txt b/doc/src/week42/week42.do.txt index 987c5215a..30bc8846d 100644 --- a/doc/src/week42/week42.do.txt +++ b/doc/src/week42/week42.do.txt @@ -1,6 +1,6 @@ TITLE: Week 42 Constructing a Neural Network code with introduction to Tensor flow AUTHOR: Morten Hjorth-Jensen {copyright, 1999-present|CC BY-NC} at Department of Physics, University of Oslo & Department of Physics and Astronomy and Facility for Rare Isotope Beams, Michigan State University -DATE: Week 42 +DATE: October 16-20, 2023 @@ -29,7 +29,7 @@ I also recommend Michael Nielsen's intuitive approach to the neural networks an !split -===== Lecture Thursday October 12 ===== +===== Lecture Thursday October 19 ===== !split