CPSC 636-600 Neural Networks
Spring 2017

I. General Information

Instructor: Dr. Yoonsuck Choe Email: choe(a)tamu.edu Office: HRBB 322B Phone: 979-845-5466 Office hours: Tue/Thu 1pm to 2pm 2pm-3pm

TA: Randall Reams Email: rcr344 at tamu.edu Office: HRBB 339 Office hours: Mon/Wed/Fri 1pm to 2pm

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:

TR 8am-9:15am, HRBB113

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:

• Simon Haykin, Neural Networks and Learning Machines, 3rd edition, Prentice Hall, Upper Saddle River, NJ, 2008. ISBN 0131471392.

However, a lot of overlapping material appear in the older edition:

• Simon Haykin, Neural Networks: A Comprehensive Foundation, Second edition, Prentice-Hall, Upper Saddle River, NJ, 1999. ISBN 0-13-273350-1.

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:

• All work should be done individually and on your own unless otherwise allowed by the instructor.
• Discussion is only allowed immediately before, during, or immediately after the class, or during the instructor's office hours.
• If you find solutions to homeworks or programming assignments on the web (or in a book, etc.), you may (or may not) use it. Please check with the instructor.
• There will be no make up exams unless it is due to a genuine emergency. Events that do not count as an emergency: Merely visiting the doctor's office without an explicit note from the office requesting absence. Interview trips that got scheduled at the last moment, etc. All make up exams, if given, will be different from the original exam. Instructor may choose to give an oral exam instead of a written exam.

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.

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:
   • Wolfgang Maass's Liquid State Machine intro
   • Hinton's Google Tech Talk on Deep Learning
   • Juergen Schmidhuber's web page
   • Ken Stanley's web page
   • Prof. Jay McClelland's lecture
   • diffeq.pdf: elementary differential equations (see page 6).
   • Jochen Fröhlich's SOM demo
   • Cover's theorem: P(N,m_1) as N increases with m_1 fixed
   • Wolfram Alpha
   • Matrix calcluls

• Lecture notes (in PDF format): all notes will be uploaded in this directory.
• It is your responsibility to download, print, and bring the notes to the class. Notes will be available 24 hours before each class.
• See the 2017 TAMU Calendar for breaks, etc.
• When reading the chapters, you do not have to memorize everything.
• More detail will be available as we go along.