Up: Dana's Home page

Mathematical Foundations of AI

Instructor: Dana H. Ballard

Office Hours: Friday 3-4pm or by appointment

Office: CSB 721

Extension: 5-3772

Text

Additional Materials

e-mail: dana@cs.rochester.edu

Overview

The goal of Artificial Intelligence has always been to imitate human intelligence but the methodology has changed radically. Initially learning was a taboo subject but now learning forms the centerpiece of AI research. Initially human brains were regarded as idiosynchratic but now human brain function is seeing major emphasis. Initially models of behavior were exclusively symbolic, but now sub-symbolic models receive the major focus. The result of all these trends is that AI researchers need a background in mathematically oriented subjects such as information theory, probability theory, and optimization theory. The goal of this course is to introduce this background in order to describe computational models of intelligent behavior and how they relate to structures in the brain.

Course Credit: Credit will be based on ten assignments, a midterm (10 %) and a final (15%). The assignments will be due Sunday midnight of every week. Some assignments will require computer programming in Matlab or C.

Week Date Topic Reading Assignment Instructor
0 15 Jan Introduction NatComp Ch1 Yu
1 20 Jan Probability Theory Nat Comp Ch 2 Prob ThyYu
1 22 Jan Prob Thy Expectation Maximization Notes Homework #1Yu
2 27 Jan Information Thy 1 Notes Homework #2Sprague
2 29 Jan Information Thy 2 NotesSprague
3 3 FebLearning Thy1 Haykin 2.14 Notes Prob SetOgihara
3 5 Feb Learning Thy 2 NatComp Ch1Ogihara
4 10 Feb Linear Algebra Notes ICA Homework Sprague
4 12 Feb Dynamical Systems NotesNatComp Ch5 Sprague
5 17 Feb OptimizationNatComp Ch5 Prob Set Yu
5 19 Feb OptimizationNatComp Ch5 Yu
6 24 Feb CAM 1: Hopfield NetsNotes61Homework Gildea
6 26 Feb Perceptrons Notes62 Conjugate Gradients Gildea
7 2 MarReview
7 4 Mar MidTerm
8 16 Mar BackProp Flying machineBallard
8 18 Mar Backprop Ballard
9 23 Mar SOM Notes8.1 Trav. SalesmanBallard
9 25 Mar Support vectors Notes8.1Ballard
10 30 Mar Markov models Notes9.1 Homework Ballard
10 1 Apr Hidden Markov models Notes9.2Ballard
11 6 Apr Reinforcement Learning Homework: RL Ballard
11 8 Apr RL2 Ballard
13 13 Apr Genetic Algorithms Notes11.1 Homework: GA Ballard
13 15 Apr Genetic Algorithms Adami pprBallard
12 20 Apr Games Homework: Games Ballard
12 22 Apr Games Ballard
14 27 May Review Front , Back , Summary Ballard