Course Description:
A study of neural computing, including basic concepts, algorithms, and applications; back propagation and counter propagation networks; Hopfield networks; associative memories; massively parallel neural architectures; adaptive resonance theory; optical neural networks; connectionist approaches.Prerequisite:
- C or higher in CS 3358: Data Structures
Course Objectives:
1. |
This course provides a comprehensive introduction to neural computing. |
2. |
Informal mathematical treatments are included when they clarify the explanation. |
3. |
Discussions will provides detailed presentations of theory, organization, and design examples. |
4. |
Currently used techniques and some of the systems used to implement these techniques will be discussed to gain an understanding of how the theory presented is used in practice. |
5. |
General discussions will provide broad and comprehensive knowledge of other advanced topics in related areas. |
6. |
Participants will learn how to evaluate the strengths and weaknesses of neural computing models. |
7. |
Participants will learn how to select a neural computing model for applications. |
8. |
Participants will learn how to define and build neural computing models. |
9. |
Participants will learn the state of the art in neural computing. |
Course Notes:
None.
Section Info:
Lecture/Lab Hours: 3 hours lecture, 0 hours lab
Offered: infrequently; it is expected that the course will be deleted in the near future (fall 2018)