The course is divided into four major units, each culminating with an applied assignment and a quiz. There is also a comprehensive final exam. References are to the following.
- BB: Deep Learning Foundations and Concepts by Christopher M. Bishop with Hugh Bishop. [BB online access link].
- GBC: Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron C. [GBC online access link]
- JM: Speech and Language Processing (3rd edition) by Dan Jurafsky and James H. Martin. [JM online access link].
- SB: Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto [SB online access link].
- RLM: Machine Learning with PyTorch and Scikit-Learn by Sebastian Raschka, Yuxi (Hayden) Liu, and Vahid M. Full book not available for free; can view [freely view RLM code examples here] or [optionally purchase RLM full text here].
Specific chapter references will be added to the schedule under the references column. Please note that the following schedule is tentative and subject to change.
| Date | Week | Topic | References | Assignments | |
|---|---|---|---|---|---|
| Unit 1: Introduction to Python and Machine Learning | |||||
| M 8/26 | 1 | 01: What is Machine Learning? | GBC 1; BB 1.1-1.2 | ||
| W 8/28 | 02: Python, NumPy, Jupyter | Jupyter Interface; Python Tutorial; NumPy Quickstart | |||
| M 9/2 | 2 | No meeting, Labor Day Holiday | |||
| W 9/4 | 03: Linear Regression and Scikit-Learn | GBC 5.1-5.2; RLM 3-4; Scikit-Learn Getting Started | Assignment 1 release | ||
| M 9/9 | 3 | 04: Logistic Regression | GBC 5.2-5.3; BB 5.2.5-5.2.6; RLM 6 (optional: GBC 5.4-5.5) | ||
| W 9/11 | 05: Logistic Regression continued | ||||
| M 9/16 | 4 | 06: Regularization and Validation, Other Models | GBC 5.2-5.3; RLM 3, 6; BB 9 | ||
| Unit 2: Artificial Neural Networks, Convolutions and Image Recognition | |||||
| W 9/18 | 07: Artificial Neural Networks | GBC 6-6.4; BB 6; RLM 12; PyTorch tutorial | |||
| F 9/20 | Assignment 1 due 5 pm | ||||
| M 9/23 | 5 | 08: Training Neural Networks: Backprop | GBC 6.5; BB 8; RLM 13; PyTorch tutorial | ||
| W 9/25 | Quiz 1 | Assignment 2 release | |||
| M 9/30 | 6 | 09: Training Neural Networks: Minibatch Stochastic Gradient Descent | GBC 7.8, 7.12, 8-8.5; BB 7; RLM 13; PyTorch tutorial | ||
| W 10/2 | 10: Convolutional Neural Networks | GBC 9-9.5; BB 10.1-10.2; RLM 14 | |||
| M 10/7 | 7 | 11: Convolutional Neural Network Wrapup and Applications | BB 10.3-10.5; RLM 14 | ||
| Unit 3: Transformers and Language Models | |||||
| W 10/9 | 12: Recurrent Neural Networks and Attention | JM 8, GBC 10, RLM 15 | |||
| M 10/14 | 8 | No meeting, Fall Break | |||
| W 10/16 | 13: Attention and Transformer Architectures | BB 12.1; RLM 16; JM 9.1-9.3 | |||
| F 10/18 | Assignment 2 due 5 pm | ||||
| M 10/21 | 9 | Quiz 2 | |||
| W 10/23 | 13: Attention and Transformer Architectures (continued) | ||||
| M 10/28 | 10 | 14: Transformer Large Language Models Part 1 | JM 9.4-9.5, 10-11; BB 12.2-12.3; RLM 16 | ||
| W 10/30 | 15: Transformer Large Language Models Part 2 | JM 9.4-9.5, 10-11; BB 12.2-12.3; RLM 16 | Assignment 3 release | ||
| M 11/4 | 11 | 16: Model Alignment, Prompting, and In-Context Learning | JM 12 | ||
| Unit 4: Reinforcement Learning | |||||
| W 11/6 | 17: Introduction to Reinforcement Learning | SB 3-4; RLM 19 | |||
| M 11/11 | 12 | 18: Model-Free Q-Learning | SB 6; RLM 19 | ||
| W 11/13 | No Meeting | ||||
| F 11/15 | Assignment 3 due 5 pm | ||||
| M 11/18 | 13 | 19: Value-Based Deep Reinforcement Learning | SB 9-10; RLM 19 | ||
| W 11/20 | Quiz 3 | ||||
| M 11/25 | 14 | 20: Implementing Value-Based Reinforcement Learning | SB 6, 9-10; RLM 19 | Assignment 4 release | |
| W 11/27 | No meeting, Thanksgiving break | ||||
| M 12/2 | 15 | 21: Policy-Based Deep Reinforcement Learning | SB 13 | ||
| W 12/4 | Quiz 4 | ||||
| F 12/6 | Assignment 4 due | ||||
| End of Classes | |||||
| M 12/9 | 16 | No meeting, reading period | |||
| W 12/11 | Comprehensive Final Exam: 9 am - noon | ||||
