6.867 Machine Learning

6.867 Machine Learning

Fall 2001

Lectures

Lectures are Tue/Thu 2:30-4pm in E37-212, first lecture on September 11

Lecture information and slides:

  • Lecture 1 (September 11) Introduction
    pdf slides or 4 per page (postscript),

  • Lecture 2 (September 13) Linear/additive models, generalization, statistical view
    (chapter 4 upto mixture models; chapters 5-5.3 & 5.6)
    pdf slides or 4 per page (postscript),

  • Lecture 3 (September 18) Active learning, classification
    (chapter 4 mixture models; chapter 6 upto maximum likelihood)
    pdf slides or 4 per page (postscript),

  • Lecture 4 (September 20) Classification
    (chapter 4 mixture models; chapter 6-6.3.1)
    pdf slides or 4 per page (postscript),

  • Lecture 5 (September 25) Classification, regularization
    (additional reading distributed later on)
    pdf slides or 4 per page (postscript),

  • Lecture 6 (September 27) Text classification, feature selection
    (chapter 6.2.2)
    pdf slides or 4 per page (postscript),

  • Lecture 7 (October 2) Feature selection, combination of methods
    pdf slides or 4 per page (postscript),

  • Lecture 8 (October 4) Boosting, support vector machines
    (see additional reading)
    pdf slides or 4 per page (postscript),

  • Lecture 9 (October 11) Support vector machines
    (see additional (optional) reading)
    pdf slides or 4 per page (postscript),

  • Lecture 10 (October 16) Complexity, model selection
    pdf slides or 4 per page (postscript),

  • Lecture 11 (October 18) Model selection, density estimation
    (Chapter 9 upto 9.2)
    pdf slides or 4 per page (postscript),

  • Lecture 12 (October 23) Mixtures, experts, and hierarchies
    (Chapter 9)
    pdf slides or 4 per page (postscript),

  • Lecture 13 (October 25) Midterm

  • Lecture 14 (October 30) Experts and non-parametric density estimation
    (Chapter 9.2)
    pdf slides or 4 per page (postscript),

  • Lecture 15 (November 1) Clustering, markov models
    pdf slides or 4 per page (postscript),

  • Lecture 16 (November 6) Markov and hidden Markov models
    (Chapter 11)
    pdf slides or 4 per page (postscript),

  • Lecture 17 (November 8) HMMs estimation and inference
    (Chapter 11; Chapter 14 recommended optional reading)
    pdf slides or 4 per page (postscript),

  • Lecture 18 (November 13) Dynamic programming, linear HMM examples
    pdf slides or 4 per page (postscript),

  • Lecture 19 (November 15) Representation, graphical models
    (Chapter 2; Chapter 8 upto 8.3.3)
    pdf slides or 4 per page (postscript),

  • Lecture 20 (November 20) Graphical models, example
    pdf slides or 4 per page (postscript),

  • Lecture 21 (November 27) Graphical models cont'd
    (Chapter 2.2; Chapter 8 upto 8.4.3)
    pdf slides or 4 per page (postscript),

  • Lecture 22 (November 29) Markov random fields
    (Chapter 2.2; Chapter 8 upto 8.4.3)
    pdf slides or 4 per page (postscript),

  • Lecture 23 (December 4) Exact inference
    (Chapter 16 upto 16.7)
    pdf slides or 4 per page (postscript),

  • Lecture 24 (December 6) Exact inference cont'd, model selection, review
    pdf slides or 4 per page (postscript),

  • Lecture 25 (December 11) Final exam