DCS 520 -- Graduate Introduction to AI

Spring 2000


Main Page Contents
Schedule
Lectures
Links

Course People
Matthew Stone

Schedule

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