Neural Network Theory and Applications
Neural Network Theory and Applications
Lecturer: Jih-Gau Juang (莊季高)
Email: jgjuang@mail.ntou.edu.tw
Phone: (02)24622192 #7210
Course ID: M1801V92
Credits: 3
Objective:
Understand the neural network structure and learning model and apply it to actual systems.
Course Prerequisites: Calculus, Engineering Mathematics, Programming.
Outline:
Introducing the principles and applications of neural networks, the course covers: 1.Network structure, 2. Learning mode, 3. Mathematical analysis, 4. Application skills.
Teaching Method: Oral lecturing, supplemented by simulation reports.
Reference:
Neural Networks and Learning Machines, Third Edition, Simon Haykin, Pearson, 2009.
Course Schedule (subject to change):
1. Introduction
2. Neural Network Structures
3. Learning Rules
4. Learning Tasks
5. Single-Layer Perceptrons
6. MultiLayer Neural Networks
7. Backpropagation Learning Algorithm
8. Advanced Backpropagation Learning Algorithm
9. Regularization Radial Basis Function Networks
10. Generalized Radial Basis Function Networks
11. Support Vector Machines
12. Hopfield Neural Networks
13. Hopfield-Tank Networks
14. Adaptive Resonance Theory
15. Deep Learning Neural Networks
Evaluation:
1.Homeworks, 10%.
2.Computer Simulations, 60%.
3.Final Exam, 30%.