Schedule
This schedule is subject to change as the semester progresses, but it will be kept up to date. Slides are linked from the lecture title. They will be made available on the day of the lecture.
| wk | Date | Topic | Readings & Milestones |
|---|---|---|---|
| 1 | Tue, Sep 5 | Introduction: Course Overview | |
| 1 | Thu, Sep 7 | Search: Graph Search | P&M §3.1–3.4 |
| 2 | Tue, Sep 12 | Search: Uninformed Search | P&M §3.5 |
| 2 | Thu, Sep 14 | Search: Heuristic Search 1 | P&M §3.6 Assignment 1 released Add/drop deadline: Sep 18 |
| 3 | Tue, Sep 19 | Search: Heuristic Search 2 | P&M §3.7–3.8 Example code: fringe.py |
| 3 | Thu, Sep 21 | Uncertainty: Probability Theory | P&M §8.1 |
| 4 | Tue, Sep 26 | Uncertainty: Conditional Independence | P&M §8.2 |
| 4 | Thu, Sep 28 | Uncertainty: Belief Networks | P&M §8.3 Assignment 1 due |
| 5 | Tue, Oct 3 | Uncertainty: Inference in Belief Networks | P&M §8.4 Assignment 2 released |
| 5 | Thu, Oct 5 | Supervised Learning: Introduction & Framework | P&M §7.1–7.2 |
| 6 | Tue, Oct 10 | Supervised Learning: Linear Models | P&M §7.3 |
| 6 | Thu, Oct 12 | Supervised Learning: Overfitting | P&M §7.4 |
| 7 | Tue, Oct 17 | Supervised Learning: Bayesian Inference | P&M §10.4, §8.6 Assignment 2 due |
| 7 | Thu, Oct 19 | Deep Learning: Neural Networks | P §3.1–3.6 |
| 8 | Tue, Oct 24 | MIDTERM | |
| 8 | Thu, Oct 26 | Deep Learning: Calculus Refresher | P §B.3–B.3.4, §B.5 |
| 9 | Tue, Oct 31 | Deep Learning: Training Neural Networks | P §7.1–7.4.1 Assignment 3 released |
| 9 | Thu, Nov 2 | Deep Learning: Image Data | P §10.1–10.4.1, §10.5 |
| 10 | Tue, Nov 7 | Deep Learning: Sequence Data | P §12.1–12.2,12.4,12.6 |
| 10 | Thu, Nov 9 | Reinforcement Learning: Markov Decision Processes | S&B §3.0–3.5 |
| Tue, Nov 14 | reading week, no class | ||
| Thu, Nov 16 | reading week, no class | ||
| 11 | Tue, Nov 21 | Reinforcement Learning: Optimality and Dynamic Programming | S&B §3.6, §4.0–4.4 Assignment 3 due |
| 11 | Thu, Nov 23 | Reinforcement Learning: Monte Carlo Prediction & Control | S&B §5.0–5.5, §5.7 Assignment 4 released |
| 12 | Tue, Nov 28 | Reinforcement Learning: TD-Learning Prediction & Control | S&B §6.0–6.5 |
| 12 | Thu, Nov 30 | Reinforcement Learning: Function Approximation & Policy Gradient Methods | S&B §9.0–9.5.4, §13.0–13.3 Withdrawal deadline: Dec 1 |
| 13 | Tue, Dec 5 | Multiagent Systems: Game Theory for Single Interactions | S&LB §3.0–3.3.2 |
| 13 | Thu, Dec 7 | Multiagent Systems: Game Theory for Sequential Interactions | S&LB §5.0–5.2.2 Assignment 4 due |
| Thu, Dec 14 at 9:00am |
FINAL EXAM | Education Gymnasium Rows 2, 4, 6 |