| Week |
Course Content |
| Week 1 |
Introduction: What is this class about? What is AI?
”Machine Learning:
Linear predictors,
Loss minimization,
Stochastic gradient descent” |
| Week 2 |
”Machine Learning:
Features, neural networks,
Gradients without tears,
Nearest Neighbors” |
| Week 3 |
”Machine Learning:
Generalization,
Unsupervised learning” |
| Week 4 |
”Search:
Tree search,
Dynamic programming,
Uniform cost search” |
| Week 5 |
”Search:
Learning costs,
A* search,
Relaxation” |
| Week 6 |
”Markov decision processes:
MDPs, Policy evaluation, value iteration” |
| Week 7 |
”Markov decision processes:
Reinforcement learning,
Monte Carlo, SARSA, Q-learning,
Exploration/exploitation, function approximation” |
| Week 8 |
”Game playing:
Minimax, expectimax,
Evaluation functions,
Alpha-beta pruning” |
| Week 9 |
”Game playing:
TD learning,
Game theory” |
| Week 10 |
”Constraint satisfaction problems:
Factor graphs,
Backtracking search,
Dynamic ordering, arc consistency” |
| Week 11 |
”Constraint satisfaction problems:
Beam search, local search
Conditional independence, variable elimination” |
| Week 12 |
”Bayesian network:
Probabilistic inference
Hidden Markov models” |
| Week 13 |
”Bayesian network:
Forward-backward
Particle filtering
Gibbs sampling” |
| Week 14 |
”Bayesian network:
Learning Bayesian networks
Laplace smoothing
Expectation Maximization” |
| Week 15 |
”Logic:
Syntax versus semantics
Propositional logic
Horn clauses” |
| Week 16 |
”Logic:
First-order logic
Resolution” |
| Week 17 |
Self-directed Learning (Video appreciation and discussion on topics related to AI) |
| Week 18 |
Self-directed Learning (Video appreciation and discussion on topics related to AI) |