Schedule

Note: topics and deadlines are subject to change.

Date		Topic	Readings	Due
08/28	Th	Introduction to Rational Agents states, actions, optimality, rationality	Ch 1-2
Module 1: Search
09/02	Tu	Search Algorithms transition model, cost function, search tree	Ch 3.1-3.3
09/04	Th	Uninformed Search 1 breadth-first, depth-first, iterative-deepening	Ch 3.3-3.4
09/09	Tu	Uninformed Search 2 best-first, uniform-cost	Ch 3.3-3.4	HW 1
09/11	Th	Informed Search a-star, heuristic, admissibility, consistency	Ch 3.5-6
09/16	Tu	Adversarial Search zero-sum, mini-max, alpha-beta pruning	Ch 5	HW 2
Module 2: Markov Decision Processes
09/18	Th	Markov Decision Processes policy, reward, transition, utility, discount	Ch 17.1
09/23	Tu	Solving MDPs 1 value, q-value, value iteration, bellman equation	Ch 17.2	HW 3
09/25	Th	Solving MDPs 2 policy iteration	Ch 17.2
09/30	Tu	Passive Reinforcement Learning bandit problems, temporal-difference learning, q-learning	Ch 22.2	Project 1 HW 4
10/02	Th	Active Reinforcement Learning exploration vs exploitation, epsilon-greedy, exploration fn	Ch 22.3
Module 3: Probabilistic Inference
10/07	Tu	Representing Uncertainty joint, marginal, and conditional probability	Ch 12.1-12.3	HW 5
10/09	Th	Bayes’ Rule chain rule, product rule, inference, independence	Ch 12.4-12.6
10/14	Tu	Midterm Exam
10/16	Th	No Class October Break
10/21	Tu	Markov Models POMDPs, belief state, markov chain	Ch 17.4, 14.1
10/23	Th	Inference in Temporal Models 1 HMMs, filtering, state estimation, prediction, smoothing	Ch 14.2	Project 2
10/28	Tu	Particle Filtering	Ch 14.4-14.5	HW 6
10/30	Th	Inference in Temporal Models 2 forward-backward, viterbi algorithm	Ch 14.3
11/04	Tu	Dynamic Bayesian Networks 1	Ch 14.4-14.5	HW 7
11/06	Th	Dynamic Bayesian Networks 2	Ch 14.4-14.5
11/11	Tu	Sampling likelihood weighting, MCMC	Ch 14.4-14.5	HW 8
Module 4: Classification and Regression
11/13	Th	Learning from Examples naive bayes	Ch 12.6, 19.3
11/18	Tu	Perceptrons back-propagation, matrix multiplication	Ch 21.1	Project 3 HW 9
11/20	Th	Neural Networks 1 hidden layer, activation function, softmax	Ch 21.1-21.2
– November Break –
12/02	Tu	Neural Networks 2 back-propagation, training/testing, over-fitting	Ch 21.1-21.2
12/04	Th	TBD	TBD
12/09	Tu	No Class		HW 10 Optional: HW 11
12/11	Th	Final Exam (Thurs, Dec 11, 2-5:30pm in Mason 211)
12/15	Mon	No Class		Project 4 (Neural Nets)