類神經網路課程大綱

教材：

Course Handouts

參考書：

1. Neural Networks, Simon Haykin, 2nd ed., Prentice-Hall, 1999
2. Neuro-Fuzzy and Soft Computing, J.R. Jang, C.T. Sun, and E. Mizutani, Prentice-Hall, 1997
3. Neural Fuzzy Systems, C.T. Lin and C.S. George Lee, Prentice-Hall, 2003
4. Neural Network and Pattern Recognition, O. Omidvar and J. Dayhoff, Academic Press, 1998

課程介紹：

This course is to cover basic neural networks and their applications.
The students are to be exposed to a broad range of domain-specific applications
study and analysis, and state-of-art research in neural networks.

課程大綱：

1. Introduction: From Brain to Artificial Intelligence.
2. Mathematics Foundation and Thresholding Logic Unit.
3.. Perceptron and Least Mean Square Learning Process.
4. Network Paradigms: The Back-propagation Network, 
5. Hopfield network
6., Competitive Learning.
7. Kohonen Feature Maps
8. Radial Basis Function Network
9. Restrict Columbia Energy
10. Principal Component Analysis
11. Maximum Eigen Filter
12. Counter-Propagation Network
13 Support Vector Machine
14. Future Directions.

成績評定：

For Adult Education Graduate Students:
1. One programming assignments. Counts 30% of course grade.
2. One midterm (20% of course grade).
3. One term paper and presentation of paper reading. (30% of course grade).
4. One final exam 20%
 
For Regulate Graduate Students:
1. Two programming assignments. Counts 40% of course grade.
2. One midterm (20% of course grade).
3. One term paper and presentation of paper reading. (20% of course grade).
4. One final exam 20%
 
* -1% per absence.