深度學習
Deep Learning
| 節 | 週四 |
|---|---|
5 13:20–14:10 | 深度學習 EC122（光復） 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
1. To learn the mathematics of deep learning techniques 2. To become familiar with deep learning tools, such as PyTorch or TensorFlow 3. To gain a solid understanding of the latest developments and applications of deep learning techniques 4. To develop practical deep learning systems
Linear Algebra, Probability Theory, Machine Learning (suggested)
無備註
(i) To submit final projects in the form of academic papers or technical reports (ii) To hold an exhibition to showcase final projects (iii) To encourage students to participate in various competitions in computer vision, gaming, data analytics, and related fields
Part One: Deep Learning (3 credits) (i) 4 Labs: 80% (completed individually; Labs 0, 2, 5, and 6) (ii) Final exam: 20% Part Two: Deep Learning Labs (3 credits) (i) 4 Labs: 50% (completed individually; Labs 1, 3, 4, and 7) (ii) Paper presentation: 25% (completed in groups of three) (iii) Final project: 25% (completed in groups of three)
教師未提供此項資料
| 週次 | 主題 |
|---|---|
| 第 1 週 | Introduction, Machine Learning Basics |
| 第 2 週 | Deep Networks - Deep Feedforward Networks - Convolutional Networks |
| 第 3 週 | Convolutional Networks |
| 第 4 週 | Convolutional Networks, Transformers |
| 第 5 週 | Linear Factor Models, Autoencoders |
| 第 6 週 | Introduction to Reinforcement Learning |
| 第 7 週 | Valued Based Reinforcement Learning |
| 第 8 週 | Recurrent and Recursive Nets, Generative Adversarial Networks |
| 第 9 週 | Diffusion Models |
| 第 10 週 | Normalizing Flows |
| 第 11 週 | Policy-based Reinforcement Learning |
| 第 12 週 | Model-based Reinforcement Learning |
| 第 13 週 | Paper Presentation |
| 第 14 週 | Paper Presentation |
| 第 15 週 | Final Exam |
| 第 16 週 | Final Project Demo |
Recommended References 1. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, 1st ed. MIT Press, 2016. 2. R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. MIT Press, 2018.
- 地點
- 教師未提供此項資料
- 時間
- 教師未提供此項資料
- 聯絡方式
- The instructor's office hours and the TA's office hours are available by appointment.