深度學習
Deep Learning
| 節 | 週五 |
|---|---|
5 13:20–14:10 | 深度學習 ED203（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 abstraction from 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 neural networks, recurrent neural networks, and transformers have been applied to the fields like computer vision, automatic speech recognition, natural language processing, data mining and bioinformatics. State-of-the-art results on various tasks have been successfully developed. This course focuses on the fundamentals and advances in deep learning, in particular generative pre-trained language model in the era of generative artificial intelligence.
Calculus, Linear Algebra, Probability & Statistics
無備註
Teaching notes or slides will be provided. Teacher assistants (蔡明晏 葉志銓 范姜伯軒 陳翊瑭 紀宇烜 林言翰 陳冠榮) will be available at ED708 at PM19:00-20:00 in week days. Appointments are required. You are encouraged to use online discussion function in E3. TAs will promptly reply your questions.
Temporary Policy: Homework (or Task Competition) (60%), Final Project (40%), Class Attendance
-
1. Machine Learning Basics 2. Deep Feedforward Networks 3. Regularization for Deep Learning 4. Recurrent Neural Networks 5. Optimization for Deep Models 6. Transformers and BERT 7. Variational Auto-Encoders 8. Generative Pre-trained Transformer 9. Large Language Models 10. Diffusion Models 11. Flow Matching
| 週次 | 主題 |
|---|---|
| 第 1 週 | National Holiday 2026-02-27(五) 時數：[2026-02-27]簡仁宗(0.00) |
| 第 2 週 | Introduction to Deep Learning 2026-03-06(五) 時數：[2026-03-06]簡仁宗(0.00) |
| 第 3 週 | Deep Neural Networks 2026-03-13(五) 時數：[2026-03-13]簡仁宗(0.00) |
| 第 4 週 | Regularization for Deep Learning 2026-03-20(五) 時數：[2026-03-20]簡仁宗(0.00) |
| 第 5 週 | Optimization for Deep Models (1st Homework) 2026-03-27(五) 時數：[2026-03-27]簡仁宗(0.00) |
| 第 6 週 | National Holiday 2026-04-03(五) 時數：[2026-04-03]簡仁宗(0.00) |
| 第 7 週 | Recurrent Neural Networks (Proposal) 2026-04-10(五) 時數：[2026-04-10]簡仁宗(0.00) |
| 第 8 週 | Attention Mechanism and Transformer 2026-04-17(五) 時數：[2026-04-17]簡仁宗(0.00) |
| 第 9 週 | Variational Auto-Encoders 2026-04-24(五) 時數：[2026-04-24]簡仁宗(0.00) |
| 第 10 週 | National Holiday 2026-05-01(五) 時數：[2026-05-01]簡仁宗(0.00) |
| 第 11 週 | Generative Large Language Models (2nd Homework) 2026-05-08(五) 時數：[2026-05-08]簡仁宗(0.00) |
| 第 12 週 | Advanced Generative Models 2026-05-15(五) 時數：[2026-05-15]簡仁宗(0.00) |
| 第 13 週 | Generation by Diffusion Processing 2026-05-22(五) 時數：[2026-05-22]簡仁宗(0.00) |
| 第 14 週 | Generation by Flow Matching 2026-05-29(五) 時數：[2026-05-29]簡仁宗(0.00) |
| 第 15 週 | Project Presentation 2026-06-05(五) 時數：[2026-06-05]簡仁宗(0.00) |
| 第 16 週 | Project Presentation 2026-06-12(五) 時數：[2026-06-12]簡仁宗(0.00) |
1. I. Goodfellow and Y. Bengio and A. Courville, Deep Learning, The MIT Press, 2016 (http://www.deeplearningbook.org) 2. S. Watanabe and J.-T. Chien, Bayesian Speech and Language Processing, Cambridge University Press, 2015. 3. J.-T. Chien, Source Separation and Machine Learning, Academic Press, 2018. 4. M.-W. Mak and J.-T. Chien, Machine Learning for Speaker Recognition, Cambridge University Press, 2020.
- 地點
- ED 708
- 時間
- PM18:00-18:30 on Monday. Appointments are required.
- 聯絡方式
- jtchien@nycu.edu.tw