Schedule
Lecture slides can be found here.
Lecture | Feb. 5 | overview and simple perceptron |
Lecture | Feb. 7 | delta rule |
Pset 0 optional | Feb. 12 | math review |
Lecture | Feb. 12 | stochastic gradient descent |
Lecture | Feb. 14 | multilayer perceptrons |
Pset 1 due | Feb. 19 | simple perceptrons |
Lecture | Feb. 19 | backpropagation |
Lecture | Feb. 21 | generalization and regularization |
Pset 2 due | Feb. 26 | multilayer perceptrons |
Lecture | Feb. 26 | convolution and pooling |
Lecture | Feb. 28 | ConvNet backprop |
Pset 3 due | Mar. 5 | black art of backprop |
Lecture | Mar. 5 | visual object recognition |
Lecture | Mar. 7 | biological vision |
Pset 4 due | Mar. 12 | LeNet |
Lecture | Mar. 12 | no class (instructor was sick) |
Lecture | Mar. 14 | image-to-image computations |
Spring break | ||
Midterm | Mar. 26 | midterm exam |
Lecture | Mar. 28 | competitive learning and clustering |
Lecture | Apr. 2 | principal component analysis |
Lecture | Apr. 4 | autoencoders and siamese nets |
Pset 5 due | Apr. 9 | dense prediction on images |
Lecture | Apr. 9 | n-grams and word embeddings |
Lecture | Apr. 11 | RNNs and LSTMs for language |
Pset 6 due | Apr. 16 | unsupervised learning |
Lecture | Apr. 16 | backprop through time |
Lecture | Apr. 18 | "Teaching a car to drive" (Larry Jackel) |
Pset 7 due | Apr. 23 | word embeddings |
Lecture | Apr. 23 | policy gradient |
Lecture | Apr. 25 | Markov decision processes |
Pset 8 due | Apr. 30 | language modeling |
Lecture | Apr. 30 | value iteration |
Lecture | May 2 | final review |
Pset 9 due | May 7 | reinforcement learning |
Final | TBA | final exam |
</div>