Machine Learning Resources: Tutorials

Suggestions welcome

Tutorials

• Bayes networks
  • A Tutorial on Learning Bayesian Networks
    • David Heckerman, Technical Report

• Evaluation
  • Statistical Evaluation of Classifiers (David Jensen & Olivier Gascuel)

• General
  • Machine Learning (67 pages, 272K)
    • David W. Aha, 1995 AI & Statistics Workshop (1/95)
    • Annotated Bibliography (21 pages, 336K)
  • Machine Learning: Issues, Answers and Quandries
    • Tom Dieterich, AAAI-91
  • Learning Methods for Prediction, Classification, Novelty Detection and Time Series Analysis
    • Geoff Hinton (9/20-21/96), Michael Jordan (12/14-15/96)

• Inductive Logic Programming
  • Machine Learning and Inductive Logic Programming for Multi-Agent Systems (Dimitar Kazakov; ACAI-01; Prague; July 2001)

• Knowledge discovery in databases
  • IJCAI-95 Tutorial
    • Usama Fayyad & Evangelos Simoudis
  • Crossing the Chasm: From Academic Machine Learning to Commercial Data Mining (Ron Kohavi, ICML-98 invited talk)

• Lazy Learning (e.g., case-based, instance-based, memory-based)
  • Elementary Memory-based

• Logic representations
  • Logical Approaches to Machine Learning
    • Peter Flach, Tilburg University

• Natural language processing
  • Automated Text Categorization
    • Fabrizio Sebastiani, tutorial given at several conferences based on Sebastiani, ACM Computing Surveys, 2002
  • Learning Over Natural Language Text (Tom Mitchell, AI&Stats 1997 Tutorial)
    • 4 slides per page

• Neural Networks
  • Backpropagation
    • Backpropagator's Review (Don Tveter)
    • Backpropagation Tutorial

• Probabilistic reasoning
  • Learning with Graphical Models
    • Wray Buntine
    • Probabilities in AI Summer School, 1994
  • An Introduction to Variational Methods for Graphical Models (Michael Jordan, Zoubin Ghahramani, Tommi Jaakola, & Lawrence Saul)

• Reinforcement learning
  • Reinforcement Learning: A Tutorial (Mance E. Harmon)
  • Reinforcement Learning
    • Leslie P. Kaelbling, Michael L. Littmann, & Andrew W. Moore
    • Four pages per slide
  • Markov Decision Processes as a Foundation for Intelligent Agents
    • Leslie P. Kaelbling
    • AAAI-94 Invited Talk
    • Four pages per slide