人工智慧原理
Principles of Artificial Intelligence
| 節 | 週二 | 週四 |
|---|---|---|
3 10:10–11:00 | 人工智慧原理 ED203 2 節連堂 | |
4 11:10–12:00 | ||
8 16:30–17:20 | 人工智慧原理 ED203 |
* 根據陽明交大上課時間表所列
人工智慧為當今顯學,目標是賦予機械像人類一樣甚至超越人類的智能,這其中又以利用過去資料訓練機器預測未來的機器學習最為成功。本堂課目標在提供學生人工智慧相關的原理及理論基礎,預計將分成三部分:第一部分簡介傳統的人工智能框架如search, reasoning, inference, graphical model等。第二部分介紹目前相當成功及熱門的機器學習之原理及演算法。第三部分則將介紹馬可夫決策過程及強化學習。若時間允許,本堂課也將涉獵深度學習及生成對抗網路等近期當紅的學習架構及背後的數學原理。
Probability, Linear Algebra
Kahoot! Quiz 20% Homework 50% Exam 30%
| 週次 | 主題 |
|---|---|
| 第 1 週 | Introduction |
| 第 2 週 | Review of linear algebra and probability |
| 第 3 週 | Problem solving by searching |
| 第 4 週 | Uninformed Search Strategies and informed search strategies |
| 第 5 週 | Knowledge and reasoning |
| 第 6 週 | Uncertain knowledge and reasoning |
| 第 7 週 | Inference and message passing algorithms |
| 第 8 週 | Statistical learning model and PAC learning |
| 第 9 週 | Linear predictor and boosting |
| 第 10 週 | Convex learning and regularization |
| 第 11 週 | Gradient descent and stochastic gradient descent |
| 第 12 週 | Support vector machines and kernel methods |
| 第 13 週 | Multi-armed bandits and Thompson sampling |
| 第 14 週 | Exam |
| 第 15 週 | Markov decision processes and Reinforcement learning |
| 第 16 週 | Deep neural networks |
| 第 17 週 | Project presentation |
| 第 18 週 | Project presentation |
[1] S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 3rd edition, Pearson, 2009 [2] A. Mackworth and D. Poole, Artificial Intelligence: Foundations of Computational Agents, Cambridge, 2012 Reference [3] R. Sutton and A. Barto, “Reinforcement Learning: An Introduction,” MIT Press, 2018. [4] S. Shalev-Shwartz and S. Ben-David, “Understanding Machine Learning: From Theory to Algorithms,” Cambridge University Press, 2014.
- 地點
- ED 834
- 時間
- TBA