References are to:
- BB: Deep Learning Foundations and Concepts by Christopher M. Bishop with Hugh B [BB online access link].
- JM: Speech and Language Processing (3rd edition) by Dan Jurafsky and James H. M [JM online access link]
- SB: Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto [SB online access link].
| Week | Date | In-Class | References | Assignments Due (11:59 pm) |
| 1 | W 1/7 | L01: What is Machine Learning? Linear Models | BB 1 | |
| 2 | M 1/12 | L02: Maximum Likelihood Estimation, Validation and Regularization | BB 4.1 | Recommended (nothing to turn in): Complete Setup and Background |
| W 1/14 | L03: Logistic Regression and Classification, Cross Entropy and Evaluation Metrics | BB 5-5.1.4, 5.2.5-5.2.6, and 5.4-5.4.4 | ||
| F 1/16 | ||||
| 3 | M 1/19 | MLK Jr. Holiday | HW 1 (due Tuesday due to Holiday) | |
| W 1/21 | L04: Artificial Neural Networks and the Multilayer Perceptron | BB 6.2-6.3.4, 6.3.6-6.4 | ||
| F 1/23 | ||||
| 4 | M 1/26 | L05: Backpropagation and Minibatch Stochastic Gradient Descent | BB 7.2-7.4, 8.1-8.1.3, 9.3, 9.6.1 | HW 2 |
| W 1/27 | L06: Convolutional Neural Networks and Image Recognition | BB 9.5, 10-10.2 | ||
| F 1/30 | ||||
| 5 | M 2/2 | L07: Convolutional Neural Networks and Object Detection | BB 10.3-10.5 | HW 3 |
| W 2/4 | L08: Sequence Models and the Transformer Architecture | BB 12-12.1, JM 8.1-8.7 | ||
| F 2/6 | ||||
| 6 | M 2/9 | L09: Transformer Language Models and Autoregressive Generation | BB 12.2-12.2.4, JM 7 | HW 4 |
| W 2/11 | L10: Fine-tuning, Low Rank Adaptation, KV-Caching, and Quantization | BB 12.3.5, JM 8.8 & 9, 10.4 | ||
| F 2/13 | ||||
| 7 | M 2/16 | L11: Chain of Thought, In-Context Learning, and Retrieval-Augmented Generation | JM 7.3, 9.4, 11 | HW 5 |
| W 2/18 | L12: Vision Transformers and Contrastive Learning | BB 6.3.5, 12.4 | ||
| F 2/20 | ||||
| 8 | M 2/23 | Exam 1 (required): Covers L01-09; HW 1-5 | ||
| W 2/25 | L13: Generative Models and Diffusion | BB 20 | ||
| F 2/27 | ||||
| 9 | M 3/2 | L14: Text-to-Image and Guided Diffusion | BB 12.4 | HW 6 |
| W 3/4 | L15: Markov Decision Processes | SB 3 | ||
| F 3/6 | ||||
| 10 | M 3/9 | Spring Recess | ||
| W 3/11 | Spring Recess | |||
| F 3/13 | Spring Recess | |||
| 11 | M 3/16 | L16: Value-Based Reinforcement Learning | SB 4.4, 5.2-5.3, 6.5 | |
| W 3/18 | Exam 1 Retake (optional) | |||
| F 3/20 | ||||
| 12 | M 3/23 | L17: Policy-Based Reinforcement Learning | SB 13 | HW 7 |
| W 3/25 | L18: State of the Art Models, Applications, and Projects | |||
| F 3/27 | ||||
| 13 | M 3/30 | Project Workshop 1 | HW 8 | |
| W 4/1 | Project Workshop 2 | |||
| F 4/3 | ||||
| 14 | M 4/6 | Exam 2 (required): Covers L08-17; HW 5-8 | ||
| W 4/8 | Project Workshop 3 | |||
| F 4/10 | ||||
| 15 | M 4/13 | Project Workshop 4 | ||
| W 4/15 | Project Workshop 5 | |||
| F 4/17 | ||||
| 16 | M 4/20 | Exam 2 Retake (optional) | ||
| W 4/22 | Project Workshop 6 | |||
| 17 | Su 4/26 | No Class, Reading Period | Final Project | |
