人工智慧無線通訊
Artificial Intelligence Wireless
| 節 | 週五 |
|---|---|
2 09:00–09:50 | 人工智慧無線通訊 ED525 3 節連堂 |
3 10:10–11:00 | |
4 11:10–12:00 |
* 根據陽明交大上課時間表所列
近年來多樣化的行動通訊應用,特別是由AI驅動的行動通訊應用風潮,激起了有關無線通訊未來發展的興趣。在5G全球化部署的同時,工業界與學術界已經開始針對超5G時代與未來6G進行熱烈地討論。我們預計未來6G將經歷前所未有的創新與突破,這將與先前行動通訊蜂窩網路系統有明顯的差異。特別是6G將超越現有移動物聯網概念,將支持核心網路到使用者終端設備皆具備無處不在的AI運算功能與個人化服務。同時,人工智慧將在6G通訊架構、協議、運行上的設計與優化扮演關鍵角色。 在本課程中,我們將討論未來6G的潛在技術與挑戰,以實現多樣化終端行動通訊應用,以及用於6G網路架構設計與優化的關鍵AI技術之理論與算法,並追蹤未來6G演進的關鍵趨勢。 課程內容將涵蓋六大部分: 1. Evolution for Wireless Communication 2. AI Wireless or Wireless AI Applications 3. Mathematical Fundamentals in AI Wireless 4. Physical Layer Communication in AI Wireless 5. Network Management in AI Wireless 6. Network Operation in AI Wireless Course Descriptions and Objectives: In recent years, diversified mobile communication applications, especially the trend of mobile communication applications driven by AI, have aroused interest in the future development of wireless communication. At the same time as the global deployment of 5G, industry and academia have begun a lively discussion on the ultra 5G era and the future 6G. We expect that 6G will experience unprecedented innovations and breakthroughs in the future, which will be significantly different from previous mobile communication cellular network systems. In particular, 6G will go beyond the existing mobile Internet of Things concept and will support the ubiquitous AI computing functions and personalized services from the core network to user terminal equipment. At the same time, artificial intelligence will play a key role in the design and optimization of 6G communication architecture, protocols, and operations. In this course, we will discuss the potential technologies and challenges of 6G in the future in order to achieve a variety of terminal mobile communication applications, as well as theories and algorithms of key AI technologies for the design and optimization of 6G network architectures, and track the future evolution of 6G Key trends. The course content will cover six parts: 1. Evolution for Wireless Communication 2. AI Wireless or Wireless AI Applications 3. Mathematical Fundamentals in AI Wireless 4. Physical Layer Communication in AI Wireless 5. Network Management in AI Wireless 6. Network Operation in AI Wireless
數位通訊、人本計算 、機器學習
學期作業:每周一次 考試:期中考、期末專題 • Assignments: 25% • Mid-Term: 35% • Final Project 35% • Class Participation 5%
| 週次 | 主題 |
|---|---|
| 第 1 週 | Part 1 – Evolution for Wireless Communication • Introduction to 6G Wireless and its Relation to AI/ML • Review of Key Physical Layer Communications Techniques in 5G Wireless • Review of Key Network Layer Communications Techniques in 5G Wireless |
| 第 2 週 | Part 2 – AI Wireless or Wireless AI Applications • Smart Phone based AI Applications • Machine Learning in Smart Phone |
| 第 3 週 | Part 3 – Mathematical Fundamentals in AI Wireless Optimization Part 1 • Preliminary Review • Block Structured Optimization • Alternating Direction Method of Multipliers (ADMM) |
| 第 4 週 | Optimization Part 2 • Mix Integer Programming • Sparse Optimization |
| 第 5 週 | Overview on Machine Learning • Machine Learning Basics • Deep Learning Basics • Multi-Agent Reinforcement Learning |
| 第 6 週 | Part 4 – Physical Layer Communication in AI Wireless • Power of Deep Learning (DL) in Physical Layer Communications |
| 第 7 週 | • Model-Driven DL in Physical Layer Communications |
| 第 8 週 | • DL End-to-End Wireless Systems |
| 第 9 週 | Midterm Exam |
| 第 10 週 | Part 5 – Network Management in AI Wireless • Deep Learning Assisted Radio Resource Optimization |
| 第 11 週 | • Deep Reinforcement Learning based Radio Resource Management |
| 第 12 週 | • Machine Learning based Interference Management |
| 第 13 週 | • Deep Reinforcement Learning based Radio Resource Management |
| 第 14 週 | Part 6 – Network Operation in AI Wireless • Machine Learning based Coverage Prediction • Machine Learning based Base Station Placement |
| 第 15 週 | • Machine Learning based Trajectory Optimization for UAV Network |
| 第 16 週 | • Machine Learning Assisted UAV High Precision Communication |
| 第 17 週 | • Multi-Agent Reinforcement Learning for Heterogeneous Wireless Network |
| 第 18 週 | Final Project |
1. Key Technologies for 5G Wireless Systems, Vincent W. S. Wong, Robert Schober, Derrick W. K. Ng, Li-Chun Wang, Cambridge 2017. (ISBN 978-1-107-17241-8) 2. Wireless AI, K. J. Ray LIU and Beibei Wang, Cambridge 2019. (ISBN 978-1-108-49786-2)
- 地點
- ED804
- 時間
- 每周三 下午 3:30-4:30 Wed. 15:30 to 16:30
- 聯絡方式
- lichun@nctu.edu.tw