CSC872: Pattern Analysis and Machine Intelligence

Fall2012 (3 UNITS)

 

Instructor: Dr. Kazunori Okada

Lec. Session

Tue: 4:00 - 6:50 pm

Lec. Location

TH 331

Office Phone

(415) 338-7687

Office

TH 911

Office Fax

(415) 338-6826

Office Hours

W: 1:20 - 2:20 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

TBD

tbd@mail.sfsu.edu

TA Office Hour

TA Office

X X:00-X:00pm

SCI 254 (CS Undergrad 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

MATLAB

Exercise 1

Note02

Exer02

Ch.2

 

 

03:09/11

AI

Problem Solving:

Search Methods

MATLAB

Exercise 2

Note03

Exer03

Ch.3-4

 

 

04:09/18

AI

Knowledge Rep.: Propositional Logic

MATLAB

Exercise 3

Note04

Exer04

Ch.7-8

HW 1

(lec01-03)

 

05:09/25

AI

Knowledge Rep:

First-Order Logic

Fast Prototype 1:

Modeling: PCA 1

Note05

Exer05

Paper 1

Ch.9

 

 

06:10/02

 

No Lecture

-----

-----------

------------

 

07:10/09

PR

Bayesian Framework

Fast Prototype 1:

Modeling: PCA 2

Note06

Exer06

Ch.13-14, 20

HW 2

(lec04-06)

 

08:10/16

PR

Statistical Modeling:

Non-Parametric

Fast Prototype 1:

Modeling: PCA 3

Note07

Exer07

Ch.20

 

 

09:10/23

PR

Statistical Modeling: Parametric

Fast Prototype 2:

Segmentation: MS 1

Note08

Exer08

Paper 2

Ch.20

HW 3

(lec07-08)

 

10:10/30

PR

Statistical Modeling:

Mixture Models

Fast Prototype 2:

Segmentation: MS 2

Note09

Exer09

 

 

P-Topic

(10/30)

11:11/06

ML

Machine Learning Framework

Fast Prototype 2:

Segmentation: MS 3

Note10

Exer10

Ch.14,

18

HW 4

(lec09-10)

 

12:11/13

ML

Supervised Learning:

Classification

Fast Prototype 3:

Classify: LDA 1

Note11

Exer11

Paper 3

Ch.3

 

 

13:11/20

 

Thanksgiving Recession

-----

-----------

------------

 

14:11/27

ML

Supervised Learning:

Regression

Fast Prototype 3:

Classify: LDA 2

Note12

Exer12

Ch.3

HW 5

(lec11-12)

 

15:12/04

NN

Neural Network:

Functional Learning

Fast Prototype 3:

Classify: LDA 3

Note13

Exer13

Ch.20

 

 

16:12/11

CON

Project

Final Presentation 1

Project

Final Presentation 2

Pres01

Pres02

-----------

------------

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 intricately 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 hands-on prototyping 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.

 

 

 

Final Project

 

Literature Survey Report & Presentation:

An independent literature study project is to be carried out by each student. This assignment provides you a hands-on exercise for conducting literature review and presentation toward preparing your own publication and thesis. Each student must choose minimum of five representative articles (approved by the instructor before Oct 30), conduct 10-minute presentation (on Dec 11), and submit a survey report due on the last class meeting (on Dec 11).  Your work will be graded based on the quality and completeness of your presentation and report. Late policy specified below will apply. Read the assignment in the above lecture plan table for more details.

 

In-Class Exercises

 

MATLAB Exercises:

These exercises offer you opportunity to learn MATLAB: a popular numerical computing software tool which will be used during our fast prototyping exercises.  The instructor and TA 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.  MATLAB clones such as Octave/SciLab are possible but not recommended. A network license copy is available through COSE’s college bulk license. The TA will help you install this copy upon your request. This is a standard version however you need to be connected to a SFSU network to use it. You can also purchase a student version of MATLAB at the university bookstore. This version has some limitation however no need to connect to SFSU network to use it. Please consult the instructor upon questions about this tool. 

 

Fast Prototyping Exercises:

These in-class hands-on programming exercises are designed to help you learn how to implement and test an algorithm quickly, and to familiarize you with practical pattern recognition and computer vision applications and their solutions. Three popular algorithms (PCA for face recognition, Mean Shift for clustering/segmentation, and LDA for classification) will be implemented. One basic paper is provided for each algorithm to familiarize you with their theory. The instructor will provide data, 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. Please see above description on how to acquire the MATLAB copy.

 

 

Exams/Homework

 

Exams:

No midterm/final examinations. J

 

Homework:

Five homework assignments will be given. Their schedule is given in the above lecture plan table.  You will be asked to answer questions and solve quantitative analytical problems. Some homework involves solving difficult pen&paper analytical problems. You are advised not to procrastinate. Your solutions are to be submitted at the beginning of the next week’s class unless specified otherwise. 

           

 

Grading Policy

 

Numerical Grade Weights:

·         50%:         Homework

·         25%:         Final Report

·         10%:         Final Presentation

·         15%:         Fast Prototyping

·         (5%):        Extra Credit for completing all FP problems in class.

·         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 (3rd,2nd Ed), Russell SJ and Norvig P, Prentice Hall, 2009, 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 (3rd, 2nd Ed), Gonzalez RC, Woods RE. Prentice Hall, 2007, 2002 (Imaging)

http://www.imageprocessingplace.com/DIP-3E/dip3e_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 110, can be reached by telephone at 338-2472 (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.html

 

Kazunori Okada © 2012, All rights are reserved.