Lecture |
Feb. 6 |
overview and simple perceptron |
Lecture |
Feb. 8 |
delta rule |
Lecture |
Feb. 13 |
multilayer perceptrons |
Pset 1 due |
Feb. 15 |
simple perceptrons |
Lecture |
Feb. 15 |
backpropagation |
Lecture |
Feb. 20 |
stochastic gradient descent |
Pset 2 due |
Feb. 22 |
multilayer perceptrons |
Lecture |
Feb. 22 |
generalization and regularization |
Lecture |
Feb. 27 |
convolution and pooling |
Pset 3 due |
Mar. 1 |
black art of backprop |
Lecture |
Mar. 1 |
ConvNet backprop |
Lecture |
Mar. 6 |
visual object recognition |
Pset 4 due |
Mar. 8 |
LeNet |
Lecture |
Mar. 8 |
biological vision |
Lecture |
Mar. 13 |
midterm review |
Midterm |
Mar. 15 |
in-class exam |
Spring break |
|
|
Lecture |
Mar. 27 |
deconvolution and other primitives |
Lecture |
Mar. 29 |
image segmentation |
Lecture |
Apr. 3 |
competitive learning and clustering |
Pset 5 due |
Apr. 5 |
dense prediction on images |
Lecture |
Apr. 5 |
principal component analysis |
Lecture |
Apr. 10 |
autoencoders |
Pset 6 due |
Apr. 12 |
unsupervised learning |
Lecture |
Apr. 12 |
n-grams and word embeddings |
Lecture |
Apr. 17 |
backprop through time |
Pset 7 due |
Apr. 19 |
word embeddings |
Lecture |
Apr. 19 |
RNNs for language |
Lecture |
Apr. 24 |
policy gradient |
Pset 8 due |
Apr. 26 |
language modeling |
Lecture |
Apr. 26 |
Markov decision processes |
Lecture |
May 1 |
value iteration |
Pset 9 due |
May 3 |
reinforcement learning |
Lecture |
May 3 |
final review |
Final |
TBA |
final exam |