機器學習
Machine Learning
| 節 | 週五 |
|---|---|
5 13:20–14:10 | 機器學習 ED219 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
Machine learning, a branch of artificial intelligence, is a scientific discipline concerned with the design and development of algorithms that allow computers to evolve behaviors based on empirical data from sensor data or databases. A major focus is to automatically learn to recognize complex patterns and make intelligent decisions based on data. This course shall deliver fundamental theories of machine learning which can be applied for many intelligent information systems.
Calculus, Linear Algebra, Probability & Statistics
Lecture notes will be provided. Teacher assistants (湯宗哲, 陳遠安, 陳明彥, 劉冠汶, 孫維佑) are available at PM 19:00-20:00 in ED 912 in week days. Any questions about ML and homework are welcome. Appointments are required.
Temporary Grading Policy: Midterm Exam (28%), Final Exam (37%), Homework (35%)
| 週次 | 主題 |
|---|---|
| 第 1 週 | Introduction to Machine Learning |
| 第 2 週 | Curve Fitting & Model Selection |
| 第 3 週 | Decision Theory & Information Theory |
| 第 4 週 | Probability Functions - Binomial, Multinomial, Beta, Dirichlet, Gaussian & Student t Distributions |
| 第 5 週 | Generative Models - Least Squares & Regularized Least Squares, Maximum Likelihood, Maximum a Posteriori |
| 第 6 週 | Bayesian Linear Regression, Bayesian Model Comparison & The Evidence Framework |
| 第 7 週 | Discriminant Function - Least Squares, Fisher's Discriminant & Perceptron Algorithm |
| 第 8 週 | Discriminative Model - Logistic Regression, Laplace Approximation & Bayesian Logistic Regression |
| 第 9 週 | Midterm Exam |
| 第 10 週 | Kernel Methods & Gaussian Process |
| 第 11 週 | Sparse Kernel Methods - Large Margin Classifier |
| 第 12 週 | Support Vector Machine & Relevance Vector Machine |
| 第 13 週 | Mixture Models and EM |
| 第 14 週 | Hidden Markov Models |
| 第 15 週 | Approximate Inference |
| 第 16 週 | National Holiday |
| 第 17 週 | Final Exam |
| 第 18 週 | Supplement Teaching |
1. C. M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006. 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
- ED912
- 時間
- PM17:30-PM18:30 on Monday (with appointment)
- 聯絡方式
- jtchien@nycu.edu.tw