機器學習
Machine Learning
| 節 | 週三 |
|---|---|
5 13:20–14:10 | 機器學習 CM216 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
Many researchers consider machine learning as a promising technology towards human-level artificial intelligence. Without being explicitly programmed, the computer learns from big data set to do a lot of tasks such as image classification, speech recognition, language translation, autonomous driving, etc. This course, with the assistance of well-known free on-line courses, provides basic and general concepts of machine learning. Topics include linear regression, logistic regression, neural networks, machine learning system design and advice, support vector machines, decision tree, boosting, etc. In addition, we will discuss the benefit of multitask learning and meta-learning.
Basics of probability theory, linear algebra, and multivariable calculus Reasonably computer programming skills in Matlab/Python/numpy
https://www.coursera.org/learn/machine-learning#about http://faculty.marshall.usc.edu/gareth-james/ISL/
There are two options students can choose from. 1) 10 Homeworks: 1 Midterm test = 66.7%:33.3% 2) 8 Homeworks: 1 Midterm test: 1 Term project = 40%:20%:40% For students who decide to do both ways, they will receive the higher scores from these two grading methods.
| 週次 | 主題 |
|---|---|
| 第 1 週 | 1. Course outline, machine learning introduction, and Linear regression with one variable |
| 第 2 週 | 2. Linear regression with multiple variables |
| 第 3 週 | 3. Logistic regression |
| 第 4 週 | 4. Neural networks: representation |
| 第 5 週 | 5. Neural networks: learning |
| 第 6 週 | 6. Machine learning system design and advice |
| 第 7 週 | 7. Support Vector Machines |
| 第 8 週 | 8. Unsupervised learning and dimensionality reduction |
| 第 9 週 | 9. Anomaly detection and recommender systems |
| 第 10 週 | 10. Large scale machine learning |
| 第 11 週 | 11. Application Example: Photo OCR |
| 第 12 週 | 12. Recap, Review, and Midterm test |
| 第 13 週 | 13. Statistical learning: Tree-based methods |
| 第 14 週 | 14. Statistical learning: Boosting methods |
| 第 15 週 | 15. Multi-task learning: soft-parameter sharing |
| 第 16 週 | 16. Multi-task learning: hard-parameter sharing |
| 第 17 週 | 17. Guest Lecture: TBD |
| 第 18 週 | 18. Term project report |
Goodfellow and Yoshua Bengio and Aaron Courville. Deep Learning. MIT Press, 2016. Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R. Springer Science, 2017
- 地點
- CM517
- 時間
- on appointment
- 聯絡方式
- machingwen@nctu.edu.tw