CS 427/527, Intro to AI, Spring 2018

Instructor

• Jared Saia
• Email: "last name" at cs.unm.edu.
• Office: FEC 3120, phone: 277-5446 The best way to reach me is generally via email. I usually check email once a day around noon.
• Office Hours: Tuesday and Thursday 2:30-3:30PM; or by appointment. I'm holding office hours in the conference room 3180
• Note: I will always be available in my office during office hours. At other times, if my door is open, feel free to come in. If the door is closed, I'm probably hard at work on a paper, grant or research problem. Please come by another time or make an appointment via email.

Teaching Assistant

• Brandon Boos
• Email: "btboos" at unm.edu
• Office Hours: Wednesday 3-5p and Friday 10AM-12
• Location: Farris 2045

Class Info

Course Description

References and Text Book

Class Communications

• CS427/527 Piazza group will be used to manage communications for this class. The link contains directions for joining and accessing communications.

Tests

Projects

• Project 0: Unix Basics and Python Tutorial - DUE Monday, Jan. 22nd at 5pm
• Project 1: Search - DUE Wednesday, Feb 7th at 5pm
• Project 2: Multi-Agent Pacman - DUE Monday, Feb 19 at 5pm
• Project 3: Reinforcement Learning - DUE Friday, March 2nd at 5pm
• Project 4: Ghost Busters - DUE Friday, April 6th at midnight
• Project 5: Classification - DUE Monday, April 23rd at midnight

Homeworks

• Hw 1: Math Assessment - DUE Weds, Jan. 24 at 5pm
• For remaining homeworks and due dates, please see the class Piazza forum

Slides from Lectures:

• Lecture 1: Introduction
• Lecture 2: Search
• Lecture 3: Informed Search (A*)
• Lecture 4: Constraint Satisfaction Problems (CSP)
• Lecture 5: Constraint Satisfaction Problems (CSP 2)
• Lecture 6: Adversarial Search
• Lecture 7: Adversarial Search 2
• Lecture 8: Markov Decision Processes (MDP)
• Lecture 9: MDP 2
• Lecture 10: Reinforcement Learning
• Lecture 11: Reinforcement Learning 2
• Lecture 12: Reinforcement Learning 3
• Lecture 13: Bayes Nets 1
• Lecture 14: Bayes Nets 2
• Lecture 15: Bayes Nets - Inference
• Lecture 16: Bayes Nets - Inference/Sampling
• Lecture 17: Bayes Nets - Sampling and Decision Networks
• Lecture 18: Value of Information
• Lecture 19: Hidden Markov Models + Particle Filtering
• Lecture 20: Hidden Markov Models + Particle Filtering (This is mostly a recap of Lec 19)
• Lecture 21: Naive Bayes
• Lecture 22: Perceptrons
• Lecture 23: Deep Learning
• Lecture 24: Handling Humans
• Gradient Descent: Why does it work?

Syllabus

Prereqs

• Expertise in programming at the level of CS351 or equivalent.
• Mathematical and Algorithmic maturity at the level of CS361/362 or equivalent. For example, you should be familiar with trees, graphs, asymptotic notation, probability and basic proof techniques.