Program Overview

Overview

The Probabilistic Foundations of Artificial Intelligence program is designed to equip students with the knowledge and skills necessary to build systems that perform well in uncertain environments and unforeseen situations. The program focuses on core modeling techniques and algorithms from statistics, optimization, planning, and control, with applications in areas such as sensor networks, robotics, and the Internet. This course is tailored for upper-level undergraduate and graduate students.

Topics Covered

• Tutorial in search (BFS, DFS, A*), constraint satisfaction, and optimization
• Tutorial in logic (propositional, first-order)
• Probability
• Bayesian Networks (models, exact and approximate inference, learning)
• Temporal models (Hidden Markov Models, Dynamic Bayesian Networks)
• Probabilistic planning (MDPs, POMDPs)
• Reinforcement learning
• Combining logic and probability

Program Details

Lecture Information

• Lecture: Friday 10-12 in CHN C 14
• Recitations: Friday 13-14 (Last names A-L) and 14-15 (Last names M-Z) in HG E 41

Teaching Materials

• Textbook: S. Russell, P. Norvig. Artificial Intelligence: A Modern Approach (3rd Edition)

Homework Assignments

• Homework 1
• Homework 2
• Homework 3
• Homework 4
• Homework 5
• Homework 6

Lecture Notes

• Introduction to the course
• Uninformed search
• Informed search
• Primer in Logic
• First-order logic
• Introduction to probability
• Bayesian Networks
• Inference in Bayesian Networks
• Approximate Inference
• Temporal models: HMMs, Kalman Filters, DBNs
• Probabilistic Planning: MDPs
• Learning Bayesian Networks
• Reinforcement learning
• Logic and probability

Recitations

• Search
• Propositional Logic
• First-order Logic
• Probability
• Bayesian Networks
• Inference
• Probabilistic Planning
• Learning Bayes Nets
• Q-learning, Bandits

Relevant Readings

• Christopher M. Bishop. Pattern Recognition and Machine Learning. Springer, 2007 (optional)