深度學習
Deep Learning
| 節 | 週一 |
|---|---|
5 13:20–14:10 | 深度學習 CM212（歸仁） 3 節連堂 |
6 14:20–15:10 | |
7 15:30–16:20 |
* 根據陽明交大上課時間表所列
This course is to help students enter the field of deep learning. We will begin by studying the fundamental math theories which is needed in deep learning. Then, the theories of various neural network architectures and building blocks, including convolutional networks, gradient descent based optimizers, ... etc., will be introduced. We will also explore some use cases of deep learning.
Linear Algebra, Probability, Programming Language
無備註
Lectures, experiments, and projects
Temporary Policy: Labs, homework and quiz (done individually) 50%, Paper presentation (done in groups of 2 members) 20% and Final Project (done in groups of 2 members) 30%
教師未提供此項資料
| 週次 | 主題 |
|---|---|
| 第 1 週 | Introduction 9/14 |
| 第 2 週 | Machine Learning Basics (1/2) 9/21 |
| 第 3 週 | Machine Learning Basics (2/2) 9/28 |
| 第 4 週 | Deep Feedforward Networks 10/5 |
| 第 5 週 | Regularization for Deep Learning 10/12 |
| 第 6 週 | Optimization Deep Models for Training (1/2) 10/19 |
| 第 7 週 | Optimization Deep Models for Training (2/2) 10/26 |
| 第 8 週 | Convelutional Networks 11/2 |
| 第 9 週 | Recurrent and Recursive Nets 11/9 |
| 第 10 週 | Linear Factor Models 11/16 |
| 第 11 週 | Autoencoders 11/23 |
| 第 12 週 | Generative Adversarial Networks 11/30 |
| 第 13 週 | Structured Probabilistic Models for Deep Learning 12/7 |
| 第 14 週 | Monte Carlo Methods 12/14 |
| 第 15 週 | Deep Generative Models 12/21 |
| 第 16 週 | Paper presentation 12/28 |
| 第 17 週 | Paper presentation 1/4 |
| 第 18 週 | Paper presentation 1/11 |
1. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, The MIT Press, 2016 2. François Chollet, Deep Learning with Python, Manning Publications, 2017
- 地點
- My office
- 時間
- Tuesday 9:00AM-11:00AM
- 聯絡方式
- jenjee@nctu.edu.tw