深度學習
Deep Learning
| 節 | 週一 |
|---|---|
5 13:20–14:10 | 深度學習 CM216 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, regularization, RNNs, Autoencoders, GANs, attention mechanisms ... etc., will be introduced. We will also explore some use cases of deep learning.
Linear Algebra, Probability, Programming Language
Lectures, labs, experiments, and projects
Temporary Policy: Labs and quiz (done individually) 75%, Paper study & presentation (done in groups of 1-2 members) 10%, Final project 15% and Attendance (for reference)
| 週次 | 主題 |
|---|---|
| 第 1 週 | Introduction |
| 第 2 週 | Machine Learning Basics (1/2) |
| 第 3 週 | Machine Learning Basics (2/2) |
| 第 4 週 | Deep Feedforward Networks |
| 第 5 週 | Regularization for Deep Learning |
| 第 6 週 | Optimization Deep Models for Training |
| 第 7 週 | The Convelutional Network and its Building Blocks (1/2) |
| 第 8 週 | The Convelutional Network and its Building Blocks (2/2) |
| 第 9 週 | Recurrent and Recursive Nets |
| 第 10 週 | Linear Factor Models |
| 第 11 週 | Autoencoders |
| 第 12 週 | Paper Presentations |
| 第 13 週 | Generative Adversarial Networks |
| 第 14 週 | Structured Probabilistic Models for Deep Learning |
| 第 15 週 | Monte Carlo Methods |
| 第 16 週 | Attention Mechanisms |
1. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, The MIT Press, 2016 2. François Chollet, Deep Learning with Python, Manning Publications, 2017 3. Related Publications
- 地點
- My office
- 時間
- Tuesday 3:00PM-5:00PM
- 聯絡方式
- jenjee@nycu.edu.tw