# Probabilistic Foundations of Artificial Intelligence

## Overview

How can we build systems that perform well in uncertain environments and unforeseen situations? How can we develop systems that exhibit ''intelligent'' behavior, without prescribing explicit rules? How can we build systems that learn from experience in order to improve their performance? We will study core modeling techniques and algorithms from statistics, optimization, planning, and control and study applications in areas such as sensor networks, robotics, and the Internet. The course is designed 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

## News

- The final recitation for the course would take place on Wednesday, 23.1.2013 at 14-16 h in CAB G 51.
- Google Discussion Group for the course

## Details

**VVZ Information:**See here.**Lecture:**Friday 10-12 in HG E 41**Recitations:**Friday 13-14 in HG E 41**Teaching assistants:**- Hastagiri Vanchinathan [hastagiri (at) inf (dot) ethz (dot) ch]
- Yuxin Chen [yuxin (dot) chen (at) inf (dot) ethz (dot) ch]
- Adish Singla [adish (dot) singla (at) inf (dot) ethz (dot) ch]

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

## Homeworks

- Homework 1 [pdf]. Solutions 1 [pdf]
- Homework 2 [pdf]. Solutions 2 [pdf]
- Homework 3 [pdf]. Solutions 3 [pdf]
- Homework 4 [pdf]. Solutions 4 [pdf]
- Homework 5 [pdf]. Solutions 5 [pdf]
- Homework 6 [pdf]. Data files: trainingData.txt and testingData.txt. Solutions 6 [pdf]

## Project

## Lecture Notes

- Sept 21: Introduction, Uninformed search (Chapters 1 and 2)
- Sept 28: Informed search (Chapters 3.1-3.6)
- Oct 5: A primer in Logic (Chapters 7.1-8.3)
- Oct 12: First order logic; (Chapters 9.1-9.2, 9.5)
- Oct 19: Intro to probability (Chapters 9.1-9.2, 9.5, 13.1-5)
- Oct 26: Bayesian Networks (Chapters 14.1-14.2); JavaBayes applet
- Nov 2: Inference in Bayesian Networks (Chapters 14.4)
- Nov 9: Approximate Inference; Information Gathering (Chapter 14.5; Bishop Chapter 8.4)
- Nov 16: Temporal models: HMMs, Kalman Filters, DBNs (Chapter 15.1-15.5)
- Nov 23: Probabilistic Planning: MDPs (Chapter 17.1-17.3). Value iteration demo (at UBC)
- Nov 30: Learning Bayesian Networks (Chapter 20.1-2).
- Dec 14: Reinforcement learning (Chapter 21.1-3). Q-learning demo (at Northwestern).
- Dec 21: Logic and probability (Chapter 14.6). Alchemy (University of Washington).

## Recitations

- Sept 28: Search [pdf]
- Oct 5: Propositional Logic [pdf]
- Oct 12: First-order Logic [pdf]
- Oct 19: Probability [pdf]; HW2 Discussion [pdf]
- Oct 26: Bayesian Networks [pdf]
- Nov 2: Project Part 1 (Milestone); HW3 Discussion [pdf]
- Nov 9: Infomation Theory [pdf]
- Nov 16: MCMC methods [pdf]; HW4 Discussion
- Nov 23: Project Part 2 [pdf]; Inference and Planning [pdf]
- Nov 30: Supervised Learning from a Probabilistic View; HW5 Discussion [pdf]
- Dec 14: Learning Bayes Nets [pdf]
- Dec 21: Multi-armed Bandits; HW6 Discussion [pdf]

## Old Exams

- PAI exam, 2011 fall [pdf]

## Relevant Readings

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