Pasted Graphic 1
Introduction to Artificial Intelligence (Fall 2013)


Instructor:
Assistant Prof. Kilian Weinberger


Details:
Course Number: CSE 511a
Credit: 3 Units
Times: 2:30pm-4:00pm Tuesdays and Thursdays (08/29/13 - 12/18/13)
Room: McDonnell Hall 162
Office Hours: Wednesdays 1PM Jolley Hall, Room 506
Exam: Wed. Dec. 18 3:30-5:30 PM
Teaching Assistants: Joshua Little, Daniel Gordon
Office Hours: Daniel Gordon Wednesday 2:30-4:00pm Jolley 431
Recitations: Joshua Little Thursday 4:00-5:00pm Jolley 431



Prerequisites:
- CSE 132, CSE 240, and CSE 241, or permission of the instructor.
- Knowledge of Python. If you are unsure about your python skills, here are some nice tutorials: Berkeley, O’Reilly, Python.org
- Some basic knowledge of statistics, probability theory and first order logic is recommended (a review lecture will be added if necessary)

Objective:
The goal of this course is to give an introduction to the field of artificial intelligence with an emphasis to provide a solid foundation to transition to more advanced courses like computer vision (CSE 559), machine learning (CSE 517A), robotics (CSE 550A) or bio-informatics (CSE 587A).

Abstract:
The discipline of artificial intelligence (AI) is concerned with building systems that think and act like humans or rationally on some absolute scale. This course is an introduction to the field, with special emphasis on sound modern methods. The topics include knowledge representation, problem solving via search, game playing, logical and probabilistic reasoning, planning, statistical machine learning (in particular bayesian statistics, graphical models, approximate inference) and machine vision. Programming exercises will concretize the key methods. The course targets graduate students and advanced undergraduates. Evaluation is based on written and programming assignments, a midterm exam, and a final exam.

Topics:
This course is organized in three chapters:
1. Deterministic AI including knowledge representation, search and planning with AI game players as an example application.
2. Reinforcement Learning. Here we focus on markov decision processes and learning from feedback.
3. Statistical Inference with an emphasize on bayesian statistics, graphical models (bayes nets) and approximate inference methods.

Pacman Competition:
This course will feature a Pacman Capture the Flag competition. The goal is to design an automated agent that eats the other player’s dots, while avoiding the ghosts of the opponent. The winner will obtain extra course credits, respect, infinite fame and unbounded sex appeal.






Course Book:
The main book is Russel and Norvig, Artificial Intelligence A Modern Approach (Third or second Edition). For a short time we will also use Sutton and Barto’s Reinforcement Learning: An Introduction.







Acknowledgements:
Many many thanks do Dan Klein and John DeNero for sharing their wonderful course materials.