深度學習實驗
Deep Learning Labs
| 節 | 週二 |
|---|---|
A 18:30–19:20 | 深度學習實驗 EC114 3 節連堂 |
B 19:30–20:20 | |
C 20:30–21:20 |
* 根據陽明交大上課時間表所列
(1) To understand the maths of deep learning techniques (2) To familiarize with deep learning tools, such as PyTorch, TensorFlow, etc. (3) To understand the latest developments and applications of deep learning techniques (4) To develop practical working systems
Linear Algebra, Probability Theory, Machine Learning (suggested)
分組方式 2人/組(Paper and Final) 1人/組(Lab) 師資人力 指導教師3人 助教3人 (1) To submit final projects as academic papers (2) To hold exhibition to showcase final projects (3) To encourage students to participate in various challenges in the fields of computer vision, gaming, data analytics, etc.
Labs (done individually) 40%, Paper presentation (done in groups of 2 members) 20% Final project (done in groups of 2 members) 20% Final exam 20%
| 週次 | 主題 |
|---|---|
| 第 1 週 | No class |
| 第 2 週 | Warm-up (Python + PyTorch) |
| 第 3 週 | No class |
| 第 4 週 | D. Deep Reinforcement Learning■ Introduction to Reinforcement Learning |
| 第 5 週 | Back-Propagation (Lab 1) |
| 第 6 週 | ■ Reinforcement Learning for Lightweight Model |
| 第 7 週 | ■ Value-based Reinforcement Learning |
| 第 8 週 | 2048 TD (Lab 2) |
| 第 9 週 | Convolutional Nets (Lab 3) |
| 第 10 週 | Convolutional Nets (Lab 4) |
| 第 11 週 | Recurrent Nets and Variational autoencoders (Lab 5) |
| 第 12 週 | ■ Policy-based Reinforcement Learning |
| 第 13 週 | Deep Reinforcement Learning (Lab 6) |
| 第 14 週 | Generative Adversarial Networks (Lab 7) |
| 第 15 週 | Paper Presentation |
| 第 16 週 | Paper Presentation |
| 第 17 週 | Paper Presentation |
| 第 18 週 |
1. I. Goodfellow, Y. Bengio, and A. Courville,Deep Learning, 1st Ed., MIT Press, Dec.2016 2. R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, Nov. 2017
- 聯絡方式
- 老師 彭文孝wpeng@cs.nctu.edu.tw 吳毅成icwu@cs.nctu.edu.tw 陳永昇yschen@cs.nctu.edu.tw 助教 謝宏笙 hongsheng.cs10g@nctu.edu.tw 李政毅 franklp97531@gmail.com