CSC872: Pattern Analysis and Machine Intelligence

 

Fall2008 (3 UNITS)

 

 

Instructor: Dr. Kazunori Okada

Lec. Session

TH: 7:00 - 9:45 pm

Lec. Location

TH 331

Office Phone

(415) 338-7687

Office

TH 911

Office Fax

(415) 338-6826

Office Hours

TTH: 3:40 - 4:40 pm

Email Address

kazokada@sfsu.edu

Web Page

http://online.sfsu.edu/~kazokada/

Mailing Address

Computer Science Department, San Francisco State University
1600 Holloway Avenue San Francisco, CA 94132-4163

Teaching Assistant

Mr. Yiyi Miao

yiyim@sfsu.edu

TA Office Hour

TA Office

TH: 6:00 – 7:00 pm

SCI 241 (CS Grad Lab)

 

 

Lecture Plan (subject to change)

Week

Sub

Topic: Lecture

Topic: Exercise

Notes

Readers

Assignments

Dues

01:08/28

INT

Introduction:

PAMI Frameworks

Project

Discussion

Note01

Exer01

Ch.1

Final

Project

 

02:09/04

AI

Agent-based AI

Framework

Project

Brainstorming 1

Note02

Exer02

Ch.2

 

 

03:09/11

AI

Problem Solving:

Search Methods

Project

Brainstorming 2

Note03

Exer03

Ch..3-4

 

 

04:09/18

AI

Knowledge Rep.: Propositional Logic

Project

Brainstorming 3

Note04

Exer04

Ch.7-8

Quiz/HW 1

(lec01-03)

 

05:09/25

AI

Knowledge Rep:

First-Order Logic

MATLAB

Exercise 1

Note05

Exer05

Paper 1

Ch.9

Midterm

Report

P-Topic

(09/25)

06:10/02

PR

Bayesian Framework

MATLAB

Exercise 2

Note06

Exer06

Ch.13-14, 20

Quiz/HW 2

(lec04-05)

 

07:10/09

PR

Statistical Modeling:

Non-Parametric

Paper

Discussion 1

Note07

Exer07

Ch.20

 

Mid-R

(10/09)

08:10/16

PR

Statistical Modeling: Parametric

Fast Prototype 1:

Modeling: PCA 1

Note08

Exer08

Paper 2

Ch.20

Quiz/HW 3

(lec06-07)

 

09:10/23

PR

Statistical Modeling:

Mixture Models

Fast Prototype 1:

Modeling: PCA 2

Note09

Exer09

 

 

 

10:10/30

ML

Machine Learning Framework

Paper

Discussion 2

Note10

Exer10

Ch.14,18

Quiz/HW 4

(lec08-09)

 

11:11/06

ML

Supervised Learning:

Classification

Guest Lecture

AI in Games

Note11

Exer11

Ch.3

 

 

12:11/13

ML

Supervised Learning:

Regression

Fast Prototype 2:

Segmentation: MS 1

Note12

Exer12

Ch.3

Quiz/HW 5

(lec10-11)

 

13:11/20

NN

Neural Network:

Functional Learning

Fast Prototype 2:

Segmentation: MS 2

Note13

Exer13

Ch.20

 

 

14

 

Thanksgiving Recess

 

 

 

 

 

 

 

 

15:12/04

CON

Project

Final Presentation 1

Project

Final Presentation 2

Pres01

Pres02

 

Quiz/HW 6

(lec12-13)

 

16:12/11

CON

Project

Final Presentation 3

Course Review

Pres03

Revi01

 

 

Final-R

(12/11)

             

 

 

Basic Information

 

Course Summary:

This course offers an introduction to the modern artificial intelligence: the pattern analysis and machine intelligence (PAMI) studies.  This research field ranges over a wide variety of well-established subjects, including artificial intelligence (AI), pattern recognition (PR), machine learning (ML), neural network (NN), all of which are highly related to each other because of the shared underlying concepts and theories.  Collectively they contribute to various practical applications, such as graphics/animation, games, factory automation, robotics, video analysis/security, medical imaging, bioinformatics, data mining, to name a few.  The main goal of this course is to develop an intuitive understanding of the various fields, as well as to understand differences between them due to specific historical and application domain biases.  Through lectures together with various exercises, you will learn not only about a number of fundamental and useful PAMI techniques but also lessons on how to successfully conduct a research project.

 

Objectives:

·       Learn the foundation of PAMI studies:

o      Artificial intelligence

o      Pattern recognition

o      Machine learning

o      Neural network

·       Learn the general concepts across various fields:

o      Data and knowledge representation

o      Problem formulation

o      Problem solving

·       Become familiarized with basic algorithms in PAMI practice.

·       Become exposed to various application domains and basic literature in PAMI studies.

 

Prerequisites:

          A grade of C or better in CSC 510 and CSC 520; or Consent of Instructor.

 

 

Term Project

 

Final Project:

A guided research project is to be carried out by each student. A list of topics will be provided by the instructor.  You are, however, welcome to choose other appropriate projects upon the instructor’s approval.  Through the entire course, various exercises will guide you along the process of defining, conducting, presenting, and writing on your project (see below descriptions). Quality of your project will be evaluated based on your 10-minute presentation (Dec 4, 11) and your final report due 10pm on the last class meeting (Dec 11).  More details can be found in the separate document found in the lecture plan table.  Late policy will apply.

 

Midterm Report:

In this take-home assignment, you will 1) find at least one article in literature that relates to your final project topic and 2) write a detailed critique on it using the knowledge you learned in the class. The content of this report is expected to serve as a part of your final report.  More details on this assignment can be found by following the link in the lecture plan table.  The report is due 10pm on Oct 9.  Late policy will apply.

 

 

In-Class Exercises

 

Project Brainstorming:

On a candidate topic chosen during the first day’s project discussion, each student is to conduct a background survey and think about how to solve it.  To help you clarify your ideas and teach/learn from others, you will “moderate” an in-class informal brainstorming session (Sep 4, 11, 18). You will lead this 10-minuite discussion by presenting a very short project summary (3min) and your own questions/assumptions/hypotheses for the project.  An informal presentation is expected.  This is to bounce your ideas among your peers by posing questions.  After this exercise, you must commit to your final project topic by sending an email to the instructor & TA by no later than Sep 25 deadline.

 

Paper Critiques:

Two articles are assigned as your mandatory reading materials. You must read them carefully before the scheduled discussion sessions (see the lecture plan table). During the discussion, we will interactively go over and critique the article. These papers familiarize you with the theory and algorithm that will be implemented during the fast prototyping exercises.

 

MATLAB Exercises:

These exercises offer you opportunity to play with and learn about MATLAB: a popular numerical computing software tool which will be used during our fast prototyping exercises.  The instructor will introduce you basics of the tool and guide you through some hands-on exercises.  Please bring your own laptop with an installation of MATLAB or its clones such as Octave/SciLab.  Please consult the instructor upon questions about this tool.  You can purchase a student version of MATLAB at the university bookstore.

 

Fast Prototyping Exercises:

These are fun in-class hands-on programming exercises designed to help you learn how to quickly implement and test an algorithm and to familiarize you with practical computer vision applications and their solutions. The instructor will provide data and basic codes, followed by a brief description of tasks to be tackled.  Students are to complete a software prototype during class meetings with minimum preparation.  Please bring your own laptop with an installation of MATLAB or its clones.

 

 

Exams/Quiz/Homework

 

Exams:

No midterm/final examinations. J

 

Quiz/Homework:

Six quizzes will be given during our class meetings.  Their schedule is given in the above lecture plan table.  To prepare for the quizzes, review the materials covered by a range of lectures specified for each quiz also in the plan table.  You will also be asked to tackle some problems as homework to be completed and submitted within one week unless specified otherwise. 

           

 

Grading Policy

 

Numerical Grade Weights:

·       20%:         Class Participation (Paper Discussions, In-Class Exercises, Project Brainstorming)

·       30%:         Quiz/Homework

·       20%:         Midterm Report

·       20%:         Final Report

·       10%:         Final Presentation

·       Variable scaling for undergraduates and graduates may be considered

 

Late Policy:

·       Every late assignment will be penalized by 10% per day up to 50%.

·       After 5 days, late assignments receive zero credit.

 

 

Course Materials

 

Course Web Page:

          http://cose-stor.sfsu.edu/~kazokada/csc872/

 

Text Book:

Artificial Intelligence: A Modern Approach (2nd Ed), Russell SJ and Norvig P, Prentice Hall, 2002

            http://aima.cs.berkeley.edu/

 

Recommended Readers:

Pattern Classification (2nd Ed), Duda RO, Hart PE, Stork DG. Wiley-Interscience, 2000 (PR, ML, NN)

            http://www.wiley.com/WileyCDA/WileyTitle/productCd-0471056693.html

Neural Network for Pattern Recognition, Bishop CM. Oxford University Press, 1996 (NN, PR, ML)

            http://portal.acm.org/citation.cfm?id=525960

The Elements of Statistical Learning, Hastie T, Tibshirani R, Friedman JH. Springer, 2003 (ML)

            http://www-stat.stanford.edu/~tibs/ElemStatLearn/

Digital Image Processing (2nd Ed), Gonzalez RC, Woods RE. Prentice Hall, 2002 (Imaging)

http://www.imageprocessingplace.com/DIP-2E/dip2e_main_page.htm

 

 

Rules

 

Syllabus is Subject to Change:

This syllabus and schedule are subject to change. It is your responsibility to check on announcements made while you were absent.

 

In-Class Communication Device Rule:

Any ringing devices such as cell phones and must be turned-off in the class room. Students with a ringing device will be asked to leave the class room immediately and not allowed to come back for the class meeting.

 

Academic Integrity & Plagiarism:

Academic Integrity refers to the “integral” quality of the search for knowledge that a student undertakes. Plagiarism is a form of cheating or fraud; it occurs when a student misrepresents the work of another as his or her own. Violation to the university and departmental rules (found in below links) is a serious offence and can result in sever penalties. It is your responsibility to familiarize yourself with the following rules:

·       SFSU Policy: http://www.sfsu.edu/~bulletin/current/supp-reg.htm#ppg339

·       Computer Science Department Policy: http://cs.sfsu.edu/plagarism.html

 

Important Resources

 

Disability Accommodations:

Students with disabilities who need reasonable accommodations are encouraged to contact the instructor. The Disability Programs and Resource Center (http://www.sfsu.edu/~dprc/welcome.html) is available to facilitate the reasonable accommodations process. The DPRC, located in SSB 109, can be reached by telephone at 338-2724 (voice/TTY) or by e-mail at dprc@sfsu.edu

 

Learning Assistances:

Learning Assistance Center, located at HSS 348, offers tutoring services for various subjects. More information can be found at http://www.sfsu.edu/~lac/ and http://www.sfsu.edu/~lac/tutoring.htm

 

Kazunori Okada © 2008, All rights are reserved.