Course Information

Less frequently-used course information has moved here.

Schedule

Date	Lecture Topic	Reading	Assignments/Section Notes
W 1/23	Introduction, Course Overview, Brief history of deep networks. pptx or pdf	Introduction from Deep Learning
M 1/28	Machine learning concepts: Loss and Risk, Discriminative models, Linear and Logistic Regression. pptx or pdf	Review: sections 1.1-1.3 and 6.6-6.9 from the CS189 book (skip KL-div). Do Python/Numpy tutorial if needed.	Section 1 notes pdf
W 1/30	Bias-Variance tradeoff, Regularization, SVMs, Multiclass classification, Softmax. Cross-validation. pptx and pdf	sections 1.4-1.6, 6.10-6.11, from the CS189 book (skip Tikhonov)	Assignment 1 out
M 2/4	Optimization, Stochastic Gradient Descent. pptx and pdf	Chapter 8 of Deep Learning Optimization Notes	Section 2 notes pdf
W 2/6	Backpropagation, Convolutional Networks. pptx and pdf	Backpropagation Notes Convnet notes
M 2/11	CNN examples, Activation functions, Initialization. pptx and pdf	Convnet notes Training Neural Networks 1 Training Neural Networks 2	Project Proposal out Section 3 notes pdf
W 2/13	Training: Batch normalization, Dropout, Ensembles, Hyperparameter tuning. pptx and pdf	Training Neural Networks 2 Training Neural Networks 3
M 2/18	Holiday: President's Day
Tu 2/19			Assignment 1 due 11pm Assignment 2 out
W 2/20	Object Detection and Segmentation. pptx and pdf	Introduction to Object Detection (All sections except ParseNet, PSPNet, DeepLab, PANet and EncNet) Introduction to Semantic Segmentation Methods	Project proposal due Practice MT1 Older MT1
M 2/25	Recurrent Networks, LSTMs, applications. pptx and pdf	RNN chapter from Deep Learning Understanding LSTM Networks	Section 4 notes pdf
W 2/27	Visualizing Deep Networks. pptx and pdf	Understanding Neural Networks Through Deep Visualization Feature Visualization	Practice Mid-term Solutions
M 3/4	Midterm 1
W 3/6	Semantic Models for Text. pptx and pdf	WordToVec Skip-Thought Vectors	Project Checkpoint 1 due week of 3/11/19
M 3/11	Attention Networks. pptx and pdf	Recurrent Models of Visual Attention	Assignment 2 due 11pm Assignment 3 out Section 6 Notes pdf
W 3/13	Natural Language Translation. pptx and pdf	NMT by Jointly Learning to Align and Translate Attention is All You Need The Illustrated Transformer
M 3/18	Text Question Answering. pptx and pdf	End-to-End Memory Networks QANet	Section 7 Notes pdf
W 3/20	Neural Dialog Systems. pptx and pdf	Learning End-to-End Goal Directed Dialog BERT: Pre-training of Deep Bidirectional Transformers
3/25-29	Spring Break
M 4/1	Adversarial and Fooling Networks. pptx and pdf	Adversarial Examples Transferability/blackbox attacks Physical perturbation	Practice Midterm 2 Section 8 Notes pdf
W 4/3	Generative Models pptx and pdf	Variational Auto-Encoders Autoregressive Models Image Transformer	Assignment 3 due 11pm Assignment 4 out
Th 4/4	MT2 review session	6-8pm in room 4 LeConte
M 4/8	Generative Adversarial Networks pptx pdf	Generative Adversarial Networks DCGAN Paper Wasserstein GAN Blog Post (From GAN to WGAN)	Section 9 Notes pdf
W 4/10	Midterm 2
M 4/15	Imitation Learning pdf	End-to-End Learning for Self-Driving Cars DAGGER Adversarial Imitation Learning	No Sections
W 4/17	Reinforcement Learning: Policy Gradients pdf	Policy Gradient Methods, chapter 13 of "Reinforcement Learning"
M 4/22	Reinforcement Learning: Value-based methods pdf	DQN paper (Nature) Asynchronous Methods for Deep RL Double DQN	Section 10 Notes pdf
W 4/24	Exploration pdf	Count-Based Exploration and Intrinsic Motivation Curiosity-driven Exploration Infobot: Information Bottleneck for RL
F 4/26			Assignment 4 due 11pm
M 4/29	Learning to Learn pdf	Learning to Learn blog post Matching Networks for One-Shot Learning Model-Agnostic Meta-Learning	Section 11 Notes pdf
W 5/1	Playing Games pptx and pdf	A Survey of Monte-Carlo Tree Search Methods sections 1-3 Mastering the Game of Go without Human Knowledge
Sa 5/4			Project Poster due 11pm
Tu 5/7	Final project poster session	2-4pm in 310 Jacobs Hall	Project Poster
M 5/13			Project Report due 11pm