|
|
|
|
home · studies

| Neural Networks |
| Module Type: |
Optional |
| Module Code: |
955 |
| Syllabus: |
Characteristics, conventional concepts, intelligent control, fuzzy control, neural control.
Artificial neural networks (ANT), Perceptrons, perceptrons with feedback (Hopfield and Kohonen
networks ), neuro-fuzzy control, evolution algorithms, and applications. |
| Module Aims-Objectives: |
Understand the philosophy behind biological neural networks simulation via Artificial Intelligence
non symbolic methods and familiarization with the process of developing such systems.
Upon completing this module students will be in a position to develop distributed memory systems
characterized by the ability to learn by example, pattern recognition and error resilience. |
| Bibliography: |
• Russell D. Reed, Robert J. Marks II, “Neural Smithing: Supervised
Learning in Feedforward Artificial Neural Networks, MIT Press, 1999
• C. M. Bishop, Neural Networks for Pattern Recognition, Oxford University
Press, 1995
• L. H. Tsoukalas, and R. E. Uhrig, “Fuzzy and Neural Approaches in
Engineering�, J. Wiley & Sons, 1997
|
|
|
|
|
|
|
