類神經網路理論與實務
Neural Network Theory and Practice
學期
107-2
學分
3
學分
當期課號
5126
永久課號
ILP5134
開課單位
照明與能源光電研究所
授課教師
林秀菊
類別
選修
上課時間表
| 節 | 週三 |
|---|---|
2 09:00–09:50 | 類神經網路理論與實務 CM224 3 節連堂 |
3 10:10–11:00 | |
4 11:10–12:00 |
* 根據陽明交大上課時間表所列
概述
The purpose of this course is to help students understand the theory and applications of neural networks. Students will have the ability to solve related problems using neural networks models.
先修科目
線性代數、機率統計、工程數學
教學方式
使用MATLAB模擬
評分方式
到課(10%) Labs(20%)、筆試(35%)與期末專題(35%)
週次計畫
| 週次 | 主題 |
|---|---|
| 第 1 週 | Introduction; Labs tool introduction |
| 第 2 週 | Neuron Model and Network Architectures |
| 第 3 週 | Perceptron Learning Rule |
| 第 4 週 | Signal and Weight Vector Spaces Linear Transformations for Neural Networks |
| 第 5 週 | Supervised Hebbian Learning |
| 第 6 週 | Performance Surfaces and Optimum Points |
| 第 7 週 | Performance Optimization |
| 第 8 週 | Widrow-Hoff Learning |
| 第 9 週 | Backpropagation |
| 第 10 週 | Midterm Exam |
| 第 11 週 | Midterm Exam discussion Variations on Backpropagation |
| 第 12 週 | Generalization; |
| 第 13 週 | Competitive Networks |
| 第 14 週 | Radial Basis Networks |
| 第 15 週 | Practical Training Issues |
| 第 16 週 | Practical simulation I |
| 第 17 週 | Practical simulation II |
| 第 18 週 | Final Project or Paper Report |
教科書
Neural Network Design, 2/e Martin T Hagan, Howard B Demuth, Mark H Beale, Orlando De Jesús, 2013 Deep Learning, Ian Goodfellow and Yoshua Bengio and Aaron Courville The MIT Press 9780262035613 2016