Learning Theory Seminar
Spring 1996
![[Content]](./Gifs/index.gif)
Content:
Time and place: Thursday 12:00-13:45 Brain
Goals:
Acquiring 'hands-on' experience in some advance topics in Signal Processing, Pattern Recognition, Machine Learning and Neural Networks.
The course is intended mainly for computer science graduates and neural computation graduates.
We assume prior knowledge of linear algebra, some complex analysis,
and basic probability theory.
We recommend prior knowledge of basics in Signal Processing, Neural Networks and Learning.
The workshop will be made out of several small projects, each on a specific topic. Each project's topic will be presented generally in an 'opening' lecture, accopmanied by references, and a few weeks of work on the project...
Projects shall be variable in their extent and level depending on the students' interest and prior knowledge.
Lectures:
March 7th: Introduction and Perceptrons.
March 14th: Noisy Perceptrons and Learning.
Perceptrons:
- Hertz J., Krough A. & Palmer R.G., Introduction to the
Theory of Neural Computation., Addison-Wesley,1990.
- Seung H.S., Sompolinsky H. & Tishby N., Statistical mechanics of learning from examples , Phys. Rev. A., Vol. 45, pp. 6056-6091.
- Ex 1: Teaching Perceptrons. (postscript)
When, Where and Who?
General description
Course Schedule and References
Literature
Classnotes
Projects
Suggestions and Comments