MIT Electrical Engineering and Computer Science Fall 2000 Catalogue Supplement

6.891 Machine Learning and Neural Networks (H)

TR 2:30-4, Room 4-149; W 1, Room 34-302; F 1, Room 34-302
Professor T. Jaakkola, Room NE43-735, 3-0440
Prereq.: 6.041, 6.042J, 18.06 or familiarity with linear algebra
4-0-8

Qualifies as a subject in the Artificial Intelligence Engineering Concentration

Examines progress in machine learning and neural networks starting from perceptrons and continuing to recent work in "bayes nets" and "support vector machines." Explores basic algorithms, including back propogation, Boltzmann machines, mixtures of experts, and hidden Markov models. Emphasis on the relationship to statistical inference. Recommended prerequisites: 6.034 and 6.011 (familiarity with decision making and estimation in the presence of uncertainty and noise).