Computational Theories of Learning and
Reasoning
Fall 1999
Lectures notes will be available here as gzipped
postscripts and source (latex) files.
The style file for scribing the lectures is
here.
Most notes are based on a draft from the 97 lectures.
Ask for the draft before you start working on your lecture notes.

Lecture #1:
Introduction to Computational Learning;The PAC model
(8/31,9/2)
tex

Lecture #2:
The importance of representation: Learning 2term DNF is hard.
(9/7,9/9)
tex

Lecture #3:
Occam's Razor: VC dimension.
(9/16,9/18)
tex

Presentation #1:
Margin Distribution Bounds on Generalization
(Presented by MingHsuan Yang)
tex
(9/21,9/23)

Lecture #4:
On Line Learning(9/28,9/30)
tex

Presentation #2:
Projection Learning (Presented by Shripad
Thite)(10/7)
tex

Presentation #3:
The Robustness of pnorm algorithms
(Presented by Shaojun Wang)(10/12,10/14)

Presentation #4:
Drifting Games (Presented by TingHao Yang)(10/19)

Lecture #5:
Active Learning(10/21,10/26)
tex

Presentation #6
: Learning Automata (Presented by Vasin Punyakanok)(10/28)

Presentation #5:
Combining labeled and unlabeled data with CoTraining (Presented by Dav Zimak)(11/2)

Lecture #6:
Reasoning with Models(11/9,11/4)
tex

Lecture #7:
Learning to Reason(11/16,11/11)
tex

Presentation #7:
Learning to take Action (Presented by Oleg Pashko)
(11/11)

Lecture #8:
Introduction to Probabilistic Reasoning(11/18)
tex

Presentation #8:
Query DAGS: A paradigm for implementing
Belief Network Inference (Presented by Sun Qiang )
(11/18)

Presentation #9:
Correction of belief propagation in Gaussian
graphical models (Presented by Cedric Yau)
(11/23)
Dan Roth