|
|
|
General Information | Resources | Weekly Schedule | Lecture Notes | Example Code | Read-Only Board |
I. General Information |
Instructor:Dr. Yoonsuck Choe |
TA:There will be no TA for this class. |
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.
TR 9:35am-10:50am HRBB 126
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.
The official textbook for this class will be:However, a lot of overlapping material appear in the older edition:
- Simon Haykin, Neural Networks and Learning Machines, 3rd edition, Prentice Hall, Upper Saddle River, NJ, 2008. ISBN 0131471392.
so this could be a good, cheaper alternative.
- Simon Haykin, Neural Networks: A Comprehensive Foundation, Second edition, Prentice-Hall, Upper Saddle River, NJ, 1999. ISBN 0-13-273350-1.
Other books: see slide01.pdf.
See the Weekly Schedule section for more details.
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'.If you are absent without any prior notification to the instructor, your class participation score will be set to 0% at the very first occurrence, except for unforseen emergencies.
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.
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 the Department of Student Life, Services for Students with Disabilities, in Cain Hall or call 845-1637.
II. Resources |
III. Weekly Schedule and Class Notes |
|
|
|||||
1 | 1/17 | Introduction | Chap 1 (Intro chapter, 3rd ed) | slide01.pdf |
||
1 | 1/19 | Introduction | Chap 1 (Intro chapter, 3rd ed) | slide01.pdf |
||
2 | 1/24 | Learning process | Chap 2 (Intro chapter sections 8, 9) | slide02.pdf |
||
2 | 1/26 | Learning process | Chap 2 (Intro chapter sections 8, 9) | slide02.pdf |
||
3 | 1/31 | Learning process | Chap 2 (Intro chapter sections 8, 9) | Homework 1 assigned | slide02.pdf |
|
3 | 2/2 | Single-layer perceptrons | Chap 3 (Chap 1, Chap 3) | slide03.pdf |
||
4 | 2/7 | Single-layer perceptrons | Chap 3 (Chap 1, Chap 3) | slide03.pdf |
||
4 | 2/9 | Multi-layer perceptrions | Chap 4 | Homework 2 assigned (2/9) | Homework 1 due | slide04.pdf |
5 | 2/14 | Multi-layer perceptrions | Chap 4 | slide04.pdf |
||
5 | 2/16 | Multi-layer perceptrions | Chap 4 | slide04-suppl.pdf |
||
6 | 2/21 | Radial-basis functions | Chap 5 | Homework 2 due | slide05.pdf |
|
6 | 2/23 | Guest lecture (Tim Mann) | NIH review panel | |||
7 | 2/28 | Radial-basis functions | Chap 5 | slide05.pdf |
||
7 | 3/1 | Midterm exam (in class) | ||||
8 | 3/6 | Special topic | Biologically inspired models | Homework 3 assigned | slide06.pdf |
|
8 | 3/8 | Special topic | Biologically inspired models | slide06.pdf |
||
9 | 3/13 | Spring Break | No class | |||
9 | 3/15 | Spring Break | No class | |||
10 | 3/20 | Special topic | Intrinsic semantics through sensorimotor learning | slide06-sida.pdf |
||
10 | 3/22 | Self-organizing maps | Chap 9 | Homework 3 due | slide07.pdf |
|
11 | 3/27 | Self-organizing maps | Chap 9 | slide07.pdf slide07-suppl.pdf |
||
11 | 3/29 | Neurodynamics | Chap 14 (3rd ed. Chap 13) | Homework 4 assigned | slide08.pdf |
|
12 | 4/3 | No lecture | See Prof. Jay McLelland's online lecture | |||
12 | 4/5 | Support-vector machines | Chap 7 | slide09.pdf |
||
13 | 4/10 | Principal component analysis/Info theory | Chap 8, 10 | slide10.pdf slide11.pdf |
||
13 | 4/12 | Information-theoretic models | Chap 10 | slide11.pdf |
||
14 | 4/17 | Information-theoretic models | Chap 10, ICA | slide11.pdf slide12.pdf |
||
14 | 4/19 | Information-theoretic models | Sarma and Choe (2006), Lee and Choe (2003), Sarma (2003); Langlois and Garrouste (1997) | Homework 4 due, in class | slide12.pdf slide13.pdf |
|
15 | 4/24 | Neuroevolution | slide14.pdf |
|||
15 | 4/26 | Exam 2 (in class) | ||||
16 | 5/1 | Redefined day: No class | Liquid state machine (Reservoir computing; Wolfgang Maass); Deep Learning (Geoff Hinton; Juergen Schmidhuber) |