CS 8803 MCP
Mathematical Foundations for Computer Perception

Fall 2003

CCB 102
MWF 10:00-11:00


Description
The goal of this course is to provide necessary mathematical tools necessary to perform research in not only computer perception, but also machine learning,  robotics,  and probably any other continuous-math intensive branch of Artificial Intelligence.

 

Instructor

Aaron Bobick

afb@cc.gatech.edu

CCB 241

(404)894-8591 (never pick it up - email much better...)

Office Hours: For now, drop by or send email to schedule an appointment.

 

Teaching Assistant

Raffay Hamid
raffay@cc.gatech.edu

Office hours: TBD

 

Course Administrator

Wanda Abbott

wanda@gvu.gatech.edu

GVU Office, CCB 244 CCB 

(404)894-0075

 


General Information

This course will cover a variety of intermediate to advanced mathematical theories and practices with the intent of making students more comfortable when taking a variety of numerically oriented AI courses such as Pattern Recognition, Machine Learning, Computational Perception or any of the robotics offerings.

 


Texts

As this is a survey of relevant topics there will be no specific text.  Rather, we will make available chapters of various textbooks which in there totality will hopefully provide a good coverage.  Copies will be handed out in class; if you miss them there they will be available in the GVU office from Wanda.

 

Texts that material will be drawn from:

·        Duda, Hart, and Stork, Pattern Classification 2nd Edition, Wiley-Interscience

·        Gelb, Applied Optimal Estimation, MIT Press

·        Strang, Introduction to Applied Mathematics, Wellesley Cambridge Press

·        Press, Numerical Recipes in C, Cambridge Press

·        Strang, Linear Algebra

·        Matlab Manuals (yes, these are often unbelievably good sources of math background)

 

and more as we get to them.

 


Requirements, Collaboration, and Grading

The grades will be assessed as follows:

Problem Sets (not all PS are created equal)

70%

Final

25%

Class Participation

5%

There will be 5 or so bi-weekly problem sets that will involve some Matlab, sometimes plain old writing, and hopefully some thinking. Collaboration on problem sets is encouraged at the "white board interaction" level. That is, share ideas and technical conversation, but write your own code. All problem sets should be in on time. One late problem set is accepted late (but before the next one is due) without excuse. After that, get prior permission.

As this is a math class there will be a final, but as you can see from the grading it is not intended to be the dominant part of your grade.

Approximate Syllabus

This course is designed to be a first year or second year grad course.  The syllabus is being designed (notice I did not say has been designed – this is a work in progress) in consultation with the other numerical-AI professors and will attempt to hit concepts seen as relevant to them.  There are approximately 44 lectures this semester.  Break down should be about the following:

 

Topics

Lectures

Matrices and Lin Alg: positive definiteness, eigen everything,  SVD, rank, conditioning, null spaces

9

Probability: discrete vs continuous, lots of Gaussians, other useful densities KL-divergence, entropy,

9

E/M algorithms

3

Minimization Methods: various gradient methods, stochastic approaches,  numerical issues

6

Basic Signal Manipulation: convolution, filter theory, Fourier/spectral decomposition

6

State-based systems: recursive prediction and estimation, Kalman filtering, non-linear filtering

4

Coordinate systems:  Homogeneous, transformations, quaternions

2

Geometry: perspective, homographies, projective,

2

 

When possible we will use examples from computer vision, something close to my heart.  

 

Date

Title

Assignments

Handouts

August 18

Intro

Read Chapter 1, Strang Applied Math

Syllabus (on line);

Chapter 1, Strang  Applied Math

20

Rows, Cols, and Pivots

 

 

22

Pos Def Matrices

 

 

25

Least Squares

 

 

 


Problem sets

PS 1:  Available: Aug 26.  Due Sept 3.  PDF is here.  No matlab yet – just pencil.

PS 2:  Available: Sept 12.  Due Sept 19.  PDF is here. 

PS 3:  Available: Sept 26.  Due Oct 3.  PDF is here. 

PS 4:  Available: Oct 14.  Due Oct 22.  PDF is here. 

PS 5:  Available: Nov 4th.  Due *** NEW DATE*** Nov 14.  PDF is here.  The energy function data are available as either a MAT file or as ASCII.  Both create the variables e1, e2, and e3.

 


Matlab Tutorial Information

You were so smart you didn’t need one…..