Date Lecture Homework / Readings Logistics
Module 1: Deep Learning Basics
1/13 Lecture 1 (Jesse Thomason):
Course Introduction
[ slides | video ]
  • DL 1.1-2, 12.1-5

1/20 Lecture 2 :
Framing Problems for ML + Loss functions and Optimization
[ slides | video ]
  • DL 5.1-4, 5.7-9

1/27 No Class
2/3 Lecture 3 (Jesse Thomason):
Neural Network Overview + Convolutional Neural Networks
[ slides | video ]

Project Team Due

2/10 Lecture 4 (Jesse Thomason):
Activations, Initializations, Optimization, and Regularization + Software Tutorials (by TAs)
[ slides | video ]

PyTorch Tutorial Notebook

2/17 Lecture 5 (Jesse Thomason):
Recurrent Neural Networks
[ slides | video ]

Course Project Proposal Due

Module 2: Deep Learning Applications
2/24 Lecture 6 :
Midterm Exam
[ slides | video ]

Assignment 1 Due

3/3 Lecture 7 (Jesse Thomason):
Deep Learning for Natural Language Processing + project pitches
[ slides | video ]

3/10 Lecture 8 (Jesse Thomason):
Transformer Networks and Deep Learning for Computer Vision + midterm debrief
[ slides | video ]
  • Assignment 2 OUT

Project Survey Due

3/17 No Class (Spring Break)
3/24 Lecture 9 (Jesse Thomason):
Multimodal Deep Learning
[ slides | video ]

Module 3: Advanced Topics in Deep Learning
3/31 Lecture 10 (Jesse Thomason):
Deep Learning for Agents + paper breakouts
[ slides | video ]

Course Project Mid-Report Due, April 3Assignment 2 Due, April 3

4/7 Lecture 11 (Jesse Thomason):
Deep Reinforcement Learning + paper breakouts
[ slides | video ]

4/14 Lecture 12 (Jesse Thomason):
Deep Learning and the World + paper breakouts
[ slides | video ]

4/21 Lecture 13 (Jesse Thomason):
Team Project Presentations
[ slides | video ]

4/28 Lecture 14 :
Team Project Presentations
[ slides | video ]

No in-class exam, Final Report due Wed May 3 11:59pm