CPSC 636-600 Neural Networks
Spring 2016

NEWS: 5/1/16, 08:47AM (Sun)
Read-Only Bulletin Board.: 1/14/17, 09:32AM (Sat)

Page last modified: 1/14/17, 09:32AM Saturday.

General Information Resources Weekly Schedule Lecture Notes Example Code Read-Only Board

I. General Information

Instructor:

Dr. Yoonsuck Choe
Email: choe(a)tamu.edu
Office: HRBB 322B
Phone: 979-845-5466
Office hours: MWF 2:40pm-3:30pm.

Grader:

Anurag Garg
Email: anuraggarg04 at email.tamu.edu
* Note: there will be no TA for this class, just a grader.
* Note: Graders do not hold office hours

Prerequisite/Restrictions:

Math 304 (linear algebra) and 308 (differential equations) or approval of instructor. (Actually, if you are mildly familiar with linear algebra and have taken calculus, you should be fine.)

Prior programming experience is not a prerequisite, but there will be programming assignments. It if preferred that you already took 633 machine learning.

Lectures:

MWF 11:30am-12:20pm. ETB 1020.

Synposis:

Basic concepts in neural computing; functional equivalence and convergence properties of neural network models; associative memory models; associative, competitive and adaptive resonance models of adaptation and learning; selective applications of neural networks to vision, speech, motor control and planning; neural network modeling environments.

Textbook:

The official textbook for this class will be: However, a lot of overlapping material appear in the older edition: so this could be a good, cheaper alternative.

Other books: see slide01.pdf.

Computer Accounts and Usage:

  1. Computer accounts: if you do not have a unix account, ask for one on the CS web page.

Topics to be covered:

See the Weekly Schedule section for more details.

Grading:

  1. Exams: 60% (midterm: 30%, final: 30%).
  2. Assignments: 40% (4 written+programming assignments, 10% each). Late submissions: 1 point (out of 100) deduction per hour late.
Grading will be on the absolute scale. The cutoff for an `A' will be 90% of total score, 80% for a `B', 70% for a `C', 60% for a `D', and below 60% for an 'F'.

Attendance will be checked on a random basis. More than 3 absences will result in a deduction of 5 points (out of 100) from the final weighted total.

Academic Integrity Statement:

AGGIE HONOR CODE: An Aggie does not lie, cheat, or steal or tolerate those who do.

Upon accepting admission to Texas A&M University, a student immediately assumes a commitment to uphold the Honor Code, to accept responsibility for learning, and to follow the philosophy and rules of the Honor System. Students will be required to state their commitment on examinations, research papers, and other academic work. Ignorance of the rules does not exclude any member of the TAMU community from the requirements or the processes of the Honor System.

For additional information please visit: http://www.tamu.edu/aggiehonor/

Local Course Policy:

Students with Disabilities:

The Americans with Disabilities Act (ADA) is a federal anti-discrimination statute that provides comprehensive civil rights protection for persons with disabilities. Among other things, this legislation requires that all students with disabilities be guaranteed a learning environment that provides for reasonable accommodation of their disabilities. If you believe you have a disability requiring an accommodation, please contact Disability Services, currently located in the Disability Services building at the Student Services at White Creek complex on west campus or call 979-845-1637. For additional information, visit http://disability.tamu.edu.

II. Resources

  1. Matlab code for the examples in the text book (2nd edition): Download the ZIP archive.
  2. Linear algebra review (by Eero Simoncelli)
  3. Matlab Primer by Kermit Sigmon, University of Florida
  4. GNU Octave http://www.octave.org (compatible with Matlab)
  5. My general resources page
  6. Neural networks resources:

III. Weekly Schedule and Class Notes

Notice: Undefined variable: i in /home/faculty/choe/web_project/636-16spring/index.php on line 342 Notice: Undefined variable: i in /home/faculty/choe/web_project/636-16spring/index.php on line 391 Notice: Undefined variable: i in /home/faculty/choe/web_project/636-16spring/index.php on line 418 Notice: Undefined offset: 4 in /home/faculty/choe/web_project/636-16spring/index.php on line 395 Notice: Undefined offset: 4 in /home/faculty/choe/web_project/636-16spring/index.php on line 395 Notice: Undefined offset: 4 in /home/faculty/choe/web_project/636-16spring/index.php on line 395 Notice: Undefined offset: 4 in /home/faculty/choe/web_project/636-16spring/index.php on line 395 Notice: Undefined offset: 4 in /home/faculty/choe/web_project/636-16spring/index.php on line 395 Notice: Undefined offset: 4 in /home/faculty/choe/web_project/636-16spring/index.php on line 395 Notice: Undefined offset: 4 in /home/faculty/choe/web_project/636-16spring/index.php on line 395 Notice: Undefined offset: 4 in /home/faculty/choe/web_project/636-16spring/index.php on line 395 Notice: Undefined offset: 4 in /home/faculty/choe/web_project/636-16spring/index.php on line 395 Notice: Undefined offset: 4 in /home/faculty/choe/web_project/636-16spring/index.php on line 395
Week
Date
Topic
Reading
Assignments
Notices and Dues
Notes
1 1/18 Martin Luther King day: No class       
1 1/20 Introduction Chap 1 (Intro chapter, 3rd ed)     slide01.pdf
1 1/22 Introduction Chap 1 (Intro chapter, 3rd ed)     slide01.pdf
2 1/25 Introduction Chap 1 (Intro chapter, 3rd ed)     slide01.pdf
2 1/27 Learning process Chap 2 (Intro chapter sections 8, 9)     slide02.pdf
2 1/29 Learning process Chap 2 (Intro chapter sections 8, 9)     slide02.pdf
3 2/1 Learning process Chap 2 (Intro chapter sections 8, 9) Homework 1 assigned   slide02.pdf
3 2/3 Single-layer perceptrons Chap 3 (Chap 1, Chap 3)     slide03.pdf
3 2/5 Single-layer perceptrons Chap 3 (Chap 1, Chap 3)     slide03.pdf
4 2/8 Single-layer perceptrons Chap 3 (Chap 1, Chap 3)     slide03.pdf
4 2/10 Single-layer perceptrons Chap 3 (Chap 1, Chap 3)     slide03.pdf
4 2/12 Multi-layer perceptrions Chap 4 Homework 2 assigned Homework 1 due slide04.pdf
5 2/15 Multi-layer perceptrions Chap 4     slide04.pdf
5 2/17 Multi-layer perceptrions Chap 4     slide04.pdf
5 2/19 Multi-layer perceptrions Chap 4     slide04.pdf
6 2/22 Multi-layer perceptrions Chap 4     slide04-suppl.pdf
6 2/24 Radial-basis functions Chap 5     slide05.pdf
6 2/26 Radial-basis functions Chap 5 Homework 3 assigned Homework 2 due slide05.pdf
7 2/29 Radial-basis functions Chap 5   Homework 2 due slide05.pdf
7 3/2 Special topic Biologically inspired models     slide06.pdf
7 3/4 Special topic Biologically inspired models     slide06.pdf
8 3/7 Exam 1 (in class)       
8 3/9 Deep learning       slide-dl.pdf
8 3/11 Deep learning     Homework 3 due slide-dl.pdf
9 3/14 Spring Break No class   Notice: Undefined offset: 3 in /home/faculty/choe/web_project/636-16spring/index.php on line 384 Notice: Undefined offset: 3 in /home/faculty/choe/web_project/636-16spring/index.php on line 385   
9 3/16 Spring Break No class   Notice: Undefined offset: 3 in /home/faculty/choe/web_project/636-16spring/index.php on line 384 Notice: Undefined offset: 3 in /home/faculty/choe/web_project/636-16spring/index.php on line 385   
9 3/18 Spring Break No class   Notice: Undefined offset: 3 in /home/faculty/choe/web_project/636-16spring/index.php on line 384 Notice: Undefined offset: 3 in /home/faculty/choe/web_project/636-16spring/index.php on line 385   
10 3/21 Deep learning       slide-dl.pdf
10 3/23 Self-organizing maps Chap 9     slide07.pdf
10 3/25 Reading day: No class       
11 3/28 Self-organizing maps Chap 9 Homework 4 assigned   slide07.pdf
slide07-suppl.pdf
11 3/30 Online guest lecture (class will not meet: view the youtube lecture on your own) Visualizing and Understanding Deep Neural Networks by Matt Zeiler on YouTube Homework 4 assigned   
11 4/1 Self-organizing maps/Neurodynamics Chap 9, Chap 14 (3rd ed. Chap 13)     slide07.pdf
slide07-suppl.pdf
slide08.pdf
12 4/4 Neurodynamics Chap 14 (3rd ed. Chap 13)     slide08.pdf
12 4/6 Principal components analysis Chap 8     slide10.pdf
12 4/8 Guest lecture Jaewook Yoo: (1) Development of motor map using GCAL (LISSOM variant); (2) Evolving neural network for simple tool use.   Homework 4 due slide.pdf
13 4/11 PCA Information theoretic models Chap 8 Chap 10, ICA     slide10.pdf
13 4/13 PCA, Information theoretic models Chap 8, Chap 10, ICA Sarma and Choe (2006), Lee and Choe (2003)     slide10.pdf
slide11.pdf
13 4/15 Info theoretic models Support vector machines Chap 10, ICA; Chap 6   Homework 4 due slide11.pdf
14 4/18 Info theoretic models; ICA Support vector machines Chap 10, ICA; Chap 6     slide11.pdf
14 4/20 ICA ; Support Vector Machines Special topic ICA; Chap 6; Sensorimotor learning     slide11.pdf
slide09.pdf
14 4/22 Support Vector Machines Special topic Chap 6; Sensorimotor learning     slide09.pdf
15 4/25 Exam 2 (in class)      
15 4/27 Special topic Salient contour detection. Sarma and Choe (2006), Lee and Choe (2003) Emergence of tool use in evolved neural networks     slide12.pdf
15 4/29 Special topic Sensorimotor learning. Choe and Smith (2006), Choe et al. (2007), etc. Predictive internal dynamics     slide-sida.pdf
16 5/2 Deep learning       
16 5/4 Deep learning; Course wrap up. Class meets on 5/3 Tuesday (redefined Friday)       


$Id: index.php,v 1.4.1.8 2006/08/22 22:01:11 choe Exp $