1 |
Mon, Jan 6 |
Introduction: What is AI? |
P&M chapter 1 NO LAB THIS WEEK |
1 |
Wed, Jan 8 |
Introduction: Representational dimensions |
P&M chapter 1 |
1 |
Fri, Jan 10 |
Search: Graph search |
P&M §3.1–3.4 |
2 |
Mon, Jan 13 |
Search: Uninformed search |
P&M §3.5 NO LAB THIS WEEK |
2 |
Wed, Jan 15 |
Search: Heuristic search |
P&M §3.6 |
2 |
Fri, Jan 17 |
Search: Heuristic Search II; Branch & bound |
P&M §3.7–3.8 Add/Drop deadline |
3 |
Mon, Jan 20 |
Search: Local search |
P&M §4.7 Assignment 1 released |
3 |
Wed, Jan 22 |
Uncertainty: Probability theory |
P&M §8.1 |
3 |
Fri, Jan 24 |
Uncertainty: Conditional independence |
P&M §8.2 |
4 |
Mon, Jan 27 |
Uncertainty: Belief networks |
P&M §8.3 |
4 |
Wed, Jan 29 |
Uncertainty: Independence in belief networks |
P&M §8.4 |
4 |
Fri, Jan 31 |
Uncertainty: Inference in belief networks |
P&M §8.4 |
5 |
Mon, Feb 3 |
Causality: Causal inference |
Bar §3.4 Assignment 1 due |
5 |
Wed, Feb 5 |
Supervised learning: Intro |
P&M §7.1–7.2 |
5 |
Fri, Feb 7 |
Supervised learning: Linear models |
P&M §7.3 Assignment 2 released |
6 |
Mon, Feb 10 |
Supervised learning: Overfitting |
P&M §7.4 |
6 |
Wed, Feb 12 |
Supervised learning: Exact Bayesian models |
P&M §10.4 |
6 |
Fri, Feb 14 |
Supervised learning: Monte Carlo estimation |
P&M §8.6 |
|
Mon, Feb 17 |
Winter Reading Break, NO CLASS |
|
|
Wed, Feb 19 |
Winter Reading Break, NO CLASS |
|
|
Fri, Feb 21 |
Winter Reading Break, NO CLASS |
|
7 |
Mon, Feb 24 |
Deep learning: Calculus refresher |
GBC §4.1, 4.3 |
7 |
Wed, Feb 26 |
Deep learning: Neural networks |
GBC §6.0–6.4.1 |
7 |
Fri, Feb 28 |
Deep learning: Training Neural Networks |
GBC §6.5 Assignment 2 due |
8 |
Mon, Mar 2 |
Deep learning: Convolutional neural networks |
GBC §9.0–9.4 |
8 |
Wed, Mar 4 |
Deep learning: Recurrent neural networks |
GBC §10.0–10.2, 10.4, 10.10 |
8 |
Fri, Mar 6 |
Midterm review |
Assignment 3 released |
9 |
Mon, Mar 9 |
Midterm exam |
|
9 |
Wed, Mar 11 |
Reinforcement learning: Markov decision processes |
S&B §3.0–3.4 |
9 |
Fri, Mar 13 |
CLASS CANCELLED |
|
10 |
Mon, Mar 16 |
CLASS CANCELLED |
|
10 |
Wed, Mar 18 |
Reinforcement learning: Policies and value functions |
S&B §3.5 |
10 |
Fri, Mar 20 |
Reinforcement learning: Optimality and Policy Evaluation |
S&B §3.6, §4.0–4.2 |
11 |
Mon, Mar 23 |
Reinforcement learning: Policy Iteration and Monte Carlo Prediction |
S&B §4.3–4.4, §5.0–5.2 |
11 |
Wed, Mar 25 |
Reinforcement learning: Monte Carlo Control |
S&B §5.3–5.5, §5.7 |
11 |
Fri, Mar 27 |
Reinforcement learning: Temporal difference learning |
S&B §6.0–6.5 Assignment 3 due |
12 |
Mon, Mar 30 |
Reinforcement learning: Function approximation |
S&B §9.0–9.5.4 |
12 |
Wed, Apr 1 |
Reinforcement learning: Policy gradient |
S&B §13.0–13.3 |
12 |
Fri, Apr 3 |
Multiagent systems: Game theory for single interactions |
S&LB §3.0–3.3.2 Assignment 4 released |
13 |
Mon, Apr 6 |
Multiagent systems: Game theory for sequential interactions |
S&LB §5.0–5.2.2 |
13 |
Wed, Apr 8 |
Final exam review |
|
|
Fri, Apr 10 |
NO CLASS |
Assignment 4 due |
|
TBD |
Final exam |
CSC B2 (usual location) eClass |