CS078/CS178, Winter 2019
Deep Learning

This page contains a tentative draft of the syllabus. It will be updated frequently with current and upcoming topics. Chapter references, when available, are to the recommended course textbook, Deep Learning, by Ian Goodfellow, Yoshua Bengio and Aaron Courville.

DateTopicsReferencesOutDue
January 4Course introduction
January 7Logistic regression as a 1-neuron networkSec. 5.5, 5.7.1
January 9From single neuron to multilayer neural networksSec. 6.1-6.4HW1
January 10 (x-hour)Tutorial on MatConvNet (Yiren)
January 11Backpropagation (part 1)Sec. 6.5
January 14Backpropagation (part 2)
January 16Practical strategies for training deep models
(preprocessing,regularization)
Sec. 7.1, 8.3
January 18More strategies for training deep models
(initialization, hyper-parameters, debugging)
Sec. 8.4, 11.4, 11.5
January 21
January 23Convolutional neural networks (motivation, local connectivity,
parameter sharing)
Sec. 9.1, 9.2HW2HW1
January 25Convolutional neural networks
(striding, pooling)
Sec. 9.3
January 28Practical tricks for CNNs
(filter size, depth)
Sec. 9.4
January 30Practical tricks for CNNs
(study of popular architectures)
February 1Data scarcity:
data augmentation, transfer learning and fine tuning
DeCAF paper
February 4Dense prediction:
fully-convolutional networks (part 1)
FCN paper
February 6Dense prediction:
fully-convolutional networks (part 2)
HW3HW2
February 8Dense prediction:
transposed convolution, skip connections
February 11Recurrent neural networks (part 1)Sec. 10.1, 10.2
February 13Recurrent neural networks (part 2)Sec. 10.4, 10.5
February 15LSTMsSec. 10.7, 10.10, 10.11
February 18Advanced optimization: batch normalization,
dropout
Sec. 7.12
BN paper, dropout paper
February 20Advanced optimization:
Nesterov momentum, Adagrad, RMSProp
Sec. 8.5
HW4HW3
February 22Unsupervised learning: undercomplete and denoising
autoencoders
Sec. 14.1, 14.5, 14.9
February 25Unsupervised learning: unsupervised pretrainingSec. 15.1
February 27Self-supervised learning (part 1)
March 1Self-supervised learning (part 2)
March 4Q&A, review sessionHW4
March 6
March 9 (3pm-5pm)Final exam