深度學習
Deep Learning
| 節 | 週五 |
|---|---|
5 13:20–14:10 | 深度學習 ED219（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
Deep learning is a branch of machine learning based on a set of algorithms that attempt to model high level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and nonlinear transformations. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks and recurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks.
Calculus, Linear Algebra, Probability & Statistics
無備註
Teaching notes or slides will be provided. Teacher assistants (廖偉翔、郭哲宇、呂昱穎、王俊煒、廖勇冠、廖尉琳、郭子聖、郭俊麟) will be available at PM19:30-20:30 in ED 912 in week days.
Final Exam (35%), Homework (40%), Final Project (25%), Class Attendance (+10%)
-
1. Machine Learning Basics 2. Deep Learning Applications 3. Deep Feedforward Networks 4. Regularization for Deep Learning 5. Optimization for Deep Models 6. Convolutional Neural Networks 7. Recurrent Neural Networks 8. Auto-Encoders & Approximate Inference 9. Variational Auto-Encoders 10. Generative Adversarial Networks 11. Deep Domain Adaptation 12. Reinforcement Learning
| 週次 | 主題 |
|---|---|
| 第 1 週 | Introduction to Deep Machine Learning |
| 第 2 週 | Deep Feedforward Networks |
| 第 3 週 | Regularization for Deep Learning |
| 第 4 週 | Optimization for Deep Models |
| 第 5 週 | Optimization for Deep Models |
| 第 6 週 | Tensorflow Tutorial & Introduction to Final Project |
| 第 7 週 | Convolutional Neural Networks |
| 第 8 週 | Recurrent Neural Networks |
| 第 9 週 | Memory Networks & Attention Mechanism |
| 第 10 週 | Memory Networks & Attention Mechanism |
| 第 11 週 | Auto-Encoders & Approximate Inference |
| 第 12 週 | Variational Auto-Encoders |
| 第 13 週 | Generative Adversarial Networks |
| 第 14 週 | Generative Adversarial Networks |
| 第 15 週 | Deep Domain Adaptation/Reinforcement Learning |
| 第 16 週 | Reinforcement Learning |
| 第 17 週 | Final Exam |
| 第 18 週 | Project Presentation |
1. I. Goodfellow and Y. Bengio and A. Courville, Deep Learning, The MIT Press, 2016 (http://www.deeplearningbook.org) 2. C. M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006. 3. S. Watanabe and J.-T. Chien, Bayesian Speech and Language Processing, Cambridge University Press, 2015.
- 地點
- ED 912
- 時間
- PM17:00-18:00 on Thursday
- 聯絡方式
- jtchien@nctu.edu.tw