Topics
| Topic | Readings |
|---|---|
| A* revisited | |
| Admissibility and informedness | |
| Agents and environments | |
| Alpha-beta pruning | rn3 §5.3, lk2 §4.2 |
| Backpropagation | lk2 §11.5-11.6, rn3 §18.7.3-18.7.5 |
| Backpropagation continued | |
| Bayesian reasoning revisited | lk2 §8.4, rn3 §13.1-13.2 |
| Branch and bound | |
| Decision trees, linear models | lk2 §10.4-10.5, rn3 §18.3-18.6 |
| Entropy | lk2 §10.6-10.7 |
| Entropy and ID3 continued | ID3 algorithm |
| Ethics of AI classifiers, self-driving cars | |
| Evaluating and improving heuristics | |
| Evaluating models | Precision and recall |
| Fuzzy logic | lk2 §8.0-8.3, rn3 §14.7.3 |
| Fuzzy logic continued | |
| Game day | |
| Genetic algorithms | lk2 §12.2-12.3, rn3 §4.1.4 |
| Genetic algorithms continued | |
| Genetic-neural programming | How machines *really* learn (CGP Grey) |
| HMMs and noisy channel model continued | |
| Hidden Markov models | lk2 §13.6, lk2 §13.9, rn3 §15.1-15.3 |
| ID3 cont'd | |
| Informed search | lk2 §3.0-3.2, rn3 §3.5.1 |
| Intelligent agents | |
| Introductions, administrivia | |
| Knowledge representation | lk2 §6.0-6.1, lk2 §6.7-6.12 |
| Math proofs | |
| Minimax revisited | lk2 §4.0-4.1, rn3 §5.1-5.2 |
| Multilayer neural networks | |
| Neural networks | |
| Noisy channel model | |
| Optimal search | lk2 §3.3-3.6, rn3 §3.5 |
| Perceptron models | lk2 §11.0-11.4, rn3 §18.7-18.7.2 |
| Planning algorithms | lk2 §14.4, rn3 §10.3-10.5, rn3 §11.1 |
| Planning as search | lk2 §14.3, rn3 §10.2 |
| Planning problems | lk2 §14.0-14.2, rn3 §10.1 |
| Planning: monolithic systems vs emergent behaviour | |
| Predicate logic | lk2 §5.3-5.4 |
| Problems and problem spaces | lk2 §2.0-2.1, rn3 §3.1-3.4 |
| Production systems | rn3 §9.3, lk2 §7.1-7.3, lk2 §7.4.2 |
| Project 1 implementation design | |
| Propositional logic | lk2 §5.0-5.2, rn3 §7.1-7.5 |
| Real time/time constrained AI | |
| Representing game states, actions | |
| Responsive agents, emergent systems | |
| Search, continued | lk2 §3.7 |
| Stochastic, partially observable games | lk2 §4.3-4.4, rn3 §5.5-5.6 |
| Supervised learning | lk2 §10.0-10.3,
rn3 §18.1-18.2
How machines learn (CGP Grey) |
| Theorem proving | |
| Training and testing | |
| Unification | rn3 §9.2 |