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 Students requesting to add this course, please fill out the form.: https://forms.gle/dUYTUqiwBu1QfnmA9
Linear Algebra, Probability Theory, Machine Learning (suggested)
分組方式 3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.
Part I (3 credits) - Deep Learning 4 Labs (including Labs 0, 2, 5, and 6) (done individually) 80% Final exam 20% Part II (3 credits) - Deep Learning Labs 4 Labs (including Labs 1, 3, 4, and 7) 50% Paper presentation (done in groups of 3 members) 25% Final project (done in groups of 3 members) 25%
| 週次 | 主題 |
|---|---|
| 第 1 週 | |
| 第 2 週 | Warm-up (Lab 0) |
| 第 3 週 | Back-Propagation (Lab 1) |
| 第 4 週 | Convolutional Nets (Lab 2) |
| 第 5 週 | MaskGIT (Lab 3) |
| 第 6 週 | Recurrent and Recursive Nets |
| 第 7 週 | |
| 第 8 週 | CVAE (Lab 4) |
| 第 9 週 | Generative Adversarial Networks ＋ Discrete control (Lab 5) |
| 第 10 週 | Final Project Proposal ＋ Diffusion (Lab6) |
| 第 11 週 | Final Project Proposal |
| 第 12 週 | Continuous control (Lab 7) |
| 第 13 週 | Paper Presentation |
| 第 14 週 | Paper Presentation |
| 第 15 週 | No class |
| 第 16 週 | No class |
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. 2020