Dr Andrew P. Paplinski

CSE5301 Neuro-Fuzzy Computing (Neural Networks)

Exam: Friday, 29th October 2004, 9:00 am, 2hrs + 15 min reading
venue: 75-111

24hwr/7dys access to MATLAB is available in the lab 19/G14a.
Apply for after hours access to these labs via the myFIT web site at the URL listed below:
http://www.infotech.monash.edu.au/myfit/heat/login.cfm

Assignments/Practicals

1. Introduction to MATLAB. Basic properties of neural networks
2. Perceptron

1. Multilayer Perceptron -- Back-Propagation
2. Image coding algorithms
3. Hebbian learning

1. Competitive Learning
2. Self-Organizing Feature Maps

Lecture Notes

1. Lecture 1 - Artificial Neural Networks and their Biological Motivation
   L1 pdf

2. Lecture 2 - Basic structures and properties of Artificial Neural Networks
   L2 pdf

3. Lecture 3 - Perceptron
   L3 pdf
   MATLAB demo script: perc.m

4. Lecture 4 - ADALINE -- The Adaptive Linear Element
   L4 pdf
   MATLAB demo scripts: adln1.m ,    adlpr.m ,    adsid.m ,    adlnc.m

5. Lecture 5 - Feedforward Multilayer Neural Networks
   L5 pdf
   MATLAB demo scripts: fap2Di.m ,    fap2D.m

6. Lecture 6 - Selected Applications of the Multilayer Perceptrons
   L6 pdf
   Image processing utilities: blkM2vc.m ,    vc2blkM.m

7. Lecture 7 - Advanced Learning Algorithms for Multilayer Perceptrons
   L7 pdf,
   Nguyen-Widrow Initialization: nwini.m

8. Lecture 8 - Generalised Hebbian Learning
   L8 pdf

9. Lecture 9 - Competitive Learning
   L9 pdf
   Related MATLAB scripts:   CmpInit.m,   CmpLrn.m

10. Lecture 10 - Self-Organizing Feature Maps
    L10 pdf
    Related MATLAB scripts:   FM22.m,   sofm.m

11. Lecture 11 - Foundations of Fuzzy Logic
    L11fz pdf
    

12. Lecture 12 - Adaptive Neuro-Fuzzy Inference System
    L12fz pdf