DCS 520 -- Graduate Introduction to AI

Course People
Matthew Stone

Class MW6 (4:30-5:50) Hill 254
Office Hours W 2:00-4:00 CoRE 328

Lecture Schedule and Notes

• Jan 24
  What is AI?

• Jan 26
  Bayesian Decision Theory. Motivation and introduction.

• Jan 31
  Bayesian Decision Theory. Continuous variables, normal distributions and linear classifiers.

  Reference for Jan 24-31:
  CS 520: Bayesian Decision Theory
  Duda, Hart and Stork, 2000, Pattern Classification,
  Chapter 2, "Bayesian Decision Theory", 68pp.

• Feb 2
  Parameter Estimation. Learning from training data. Maximum Likelihood.

• Feb 7
  Parameter Estimation. Bayesian Parameter Estimation. Incremental Learning.

• Feb 9
  General Density Estimation. Nearest Neighbor Classification. Parzen Windows.

• Feb 14
  Discrete classification. Naive Bayes inference. Text classification. Smoothing.
  Assignment one out; due March 1
  Homework reference data program Revised 2/28

  Reference for Feb 2-16:
  CS 520: Bayesian Estimation
  Duda, Hart and Stork, 2000, Pattern Classification,
  Chapter 3, "Maximum Likelihood and Bayesian Estimation", 76pp.
  Also includes presentations of HMMs and belief nets.

• Feb 16
  Independence and Time. Markov models and hidden Markov models: evaluation.

• Feb 21
  Hidden Markov models: decoding. Viterbi. Part-of-speech tagging.

• Feb 23
  Hidden Markov models: training. Forward/backward. Speech and gesture recognition.

• Feb 28
  The Kalman filter. Tracking and learning with Gaussian priors.
  Web resource on the Kalman filter.

  Reference for Feb 28:
  CS 520: Kalman Filters
  Maybeck, 1979 Stochastic Models, Estimation and Control,
  Chapter 1, "Introduction", pp 1-15.

• Mar 1
  Models of hierarchical structure. Trees, CFGs and PCFGs.

• Mar 6
  Using PCFG models: inside-outside algorithm and PCFG parsing.

  Reference for Feb 16-March 6:
  CS 520: Markov Models and PCFGs for language processing
  Manning and Schuetze, 1999, Foundations of Statistical Natural Language Processing,
  From Chapter 3, "Linguistic Essentials", pp 81-109.
  From Chapter 10, "Part of speech tagging", pp 341-351.
  From Chapter 11, "PCFGs", pp 381-403.
  

• Mar 8
  Evaluating systems and probabilistic models.

  Reference for March 8:
  CS 520: Evaluation
  Cohen, 1995 Empirical Methods for Artificial Intelligence,
  Chapter 3, "Basic Issues in Experiment Design", pp 67-104.
  Chapter 6, "Performance Assessment", pp 185-234.
  

• Mar 13, Mar 15
  No class: Spring Break.

• Mar 20
  General probabilistic inference: belief nets.

• Mar 22
  Exact evaluation in belief nets.

• Mar 27
  Approximate evaluation in belief nets. Sampling conditional density.

  Reference for March 20-27:
  CS 520: Belief networks
  Russell and Norvig, 1995 Artificial Intelligence: A modern aproach,
  Chapter 15, "Probabilistic reasoning systems", pp. 436-467.

  Homework 1 answers.

• Mar 29
  Midterm

• Apr 3
  Midterm Review

• Apr 5
  Agents, decisions and utility; decision trees.

  Reference for April 5-12; April 26:
  CS 520: Decision theory
  Russell and Norvig, 1995 Artificial Intelligence: A modern aproach,
  Chapter 16, "Making simple decisions", pp. 471-493.
  From Chapter 17, "Making complex decisions", pp. 498-507.
  From Chapter 20, "Reinforcement learning", pp. 598-618.

• Apr 10
  Encoding distributions: influence diagrams.

• Apr 12
  Multiple decisions and the value of information. Active perception.

• Apr 17
  Markov decision processes: Value iteration.

  Reference for April 17-19:
  CS 520: Markov decision processes
  Howard, 1960 Dynamic Programming and Markov Processes,
  Chapters 1-3, pp. 3-31; Chapter 7, pp. 76-91.

• Apr 19
  Markov decision processes: Policy iteration.

• Apr 24
  Sensitivity analysis.

• Apr 26
  Reinforcement learning.

• May 1
  No class.

• May 10
  Final exam. Hill 254, 4:30pm.

Links

• General AI References
  • Hal's Legacy: 2001's Computer as Dream and Reality. An electronic book surveying how Kubrick and Clarke's hypothetical computer compares with the actual state of the art today.
  • The CMU Artificial Intelligence Repository collects files, programs and publications related to AI.
  • AAAI, the society for AI research has put together a web site about AI, including descriptions, references and web links.

• Cool AI Systems
  • AI technology really is being used onboard spacecraft! NASA's Deep Space 1 probe was operated by knowledge-based agent software during a test last fall.
    The algorithms and representations of this software involve industrial-strength implementations of the techniques taught in this course.
  • Researchers at NASA and the Robotics Institute at CMU have constructed an autonomous robot to find and classify meteors and other rocks in Antarctica.
  • An IBM team is using logic to guide the action of internet agents that run e-businesses.

• Robots and the Media
  • Fast, Cheap and Out of Control: The eerie documentary featuring Rod Brooks.
  • Buy Sony's entertainment robot dog.
  • Killer Robot HQ. "Survival Research Labs is among the first civilians to develop and operate a multi-user, teleoperated firing system using free software deployed over the web."

• More AI related Rutgers stuff
  • The general colloquium series of the Center for Cognitive Science presents cutting-edge research on the computational study of the mind.
  • The series on Human and Computer Vision features weekly talks by researchers spanning both human and computer vision.
  • The language acquisition, modeling and processing talk series frequently covers computational research.