CS256
Fall 2017
Lecture Notes
Topics in Artificial Intelligence
Videos of lectures are available.
Below are my lecture notes for the class so far.
They should serve as a rough guide to what was covered on any given day.
Frequently, however, I say more in class than is in these notes.
Also, I tend to dynamically correct typos on the board
that might appear in these lecture notes. So caveat emptor.
Week 1: [Aug 25  Syllabus]
Week 2: [Aug 28  What is Deep Learning?] [Aug 30  Probability, PAC Learning, Linear Algebra]
Week 3: [Sep 4  Labor Day  No Class] [Sep 6  Finish FirstPass Linear Algebra, Perceptrons].
Week 4: [Sep 11  Perceptrons Learning, Python] [Sep 13  Finish PAC result, Python]
Week 5: [Sep 18  Finish Python First Pass] [Sep 20  Perceptron Lower and Upper Bounds]
Week 6: [Sep 25  Perceptron Networks and ptime algorithms, SVMs] [Sep 27  SVM Training]
Week 7: [Oct 4  Practice Midterm 1] [Oct 6  Midterm 1]
Week 8: [Oct 9  Numpy, Pillow] [Oct 11  Neural Net Experiments, Feedforward Networks]
Week 9: [Oct 16  Cost Functions, Output Layers] [Oct 18  Minimization Methods, Hidden Units, Stochastic Gradient Descent]
Week 10: [Oct 23  Backpropagation, Tensorflow] [Oct 23  More Tensorflow, Regularization]
Week 11: [Oct 30  Practice Midterm 2] [Nov 1  Midterm 2]
Week 12: [Nov 6  More Regularization] [Nov 8  Finish Regularization, Optimization]
Week 13: [Nov 13  Finish Optimization] [Nov 15  CNNs and RNNs]
Week 14: [Nov 20  Recurrent Neural Networks] [Nov 22  Thanksgiving Break]
Week 15: [Nov 27  Finish RNNs, Neural Network Design Methodology] [Nov 29  NN Design Methodology]
Week 16: [Dec 4  Finish NN Design, NN Applications] [Dec 6  More NN Applications]
