機器學習
Machine Learning
| 節 | 週二 |
|---|---|
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
Uing popular machine learning textbooks, this course emphasizes on both the programming skills and theory of machine learning algorithms. The course content covers basic, general, and advanced machine learning concepts. Basic concepts include linear regression, decision trees, supervised learning, neural networks, cross-validation, etc.; common concepts include unsupervised learning, reinforcement learning, deep neural networks, error analysis, etc.; advanced concepts include variational inference and diffusion models.
Basics of probability theory, linear algebra, and multivariable calculus Reasonably computer programming skills in Matlab/Python/numpy.
1, Teaching students the textbook(1) chapter by chapter to help build machine learning programming skills. 2. Selecting some topics from the textbook (2)(3) for teaching to help student build machine learning theory.
Homeworks: 40% Term project proposal: 20% Term project report: 40%
| 週次 | 主題 |
|---|---|
| 第 1 週 | Part 1. Basic Machine learning concepts Course outline Chapter 1: Giving Computers the Ability to Learn from Data |
| 第 2 週 | Chapter 2: Training Simple Machine Learning Algorithms for Classification Chapter 3: A Tour of Machine Learning Classifiers Using Scikit-Learn |
| 第 3 週 | Chapter 4: Building Good Training Datasets – Data Preprocessing Chapter 5: Compressing Data via Dimensionality Reduction |
| 第 4 週 | Chapter 6: Learning Best Practices for Model Evaluation and Hyperparameter Tuning Chapter 7: Combining Different Models for Ensemble Learning |
| 第 5 週 | Part 2. General Machine Learning Concepts Chapter 8: Applying Machine Learning to Sentiment Analysis Chapter 9: Predicting Continuous Target Variables with Regression Analysis |
| 第 6 週 | Chapter 10: Working with Unlabeled Data – Clustering Analysis Chapter 11: Implementing a Multilayer Artificial Neural Network from Scratch |
| 第 7 週 | Chapter 12: Parallelizing Neural Network Training with PyTorch Chapter 13: Going Deeper – The Mechanics of PyTorch |
| 第 8 週 | Chapter 14: Classifying Images with Deep Convolutional Neural Networks Chapter 15: Modeling Sequential Data Using Recurrent Neural Networks |
| 第 9 週 | Chapter 16: Transformers – Improving Natural Language Processing with Attention Mechanisms Chapter 17: Generative Adversarial Networks for Synthesizing New Data |
| 第 10 週 | Chapter 18: Graph Neural Networks for Capturing Dependencies in Graph Structured Data |
| 第 11 週 | Chapter 19: Reinforcement Learning for Decision Making in Complex Environments |
| 第 12 週 | 12. Recap, Review, and Term project proposal |
| 第 13 週 | Part3. Advanced machine learning concepts and others *** unsupervised learning *** 13.1 K-means clustering Mixture of Gaussians (GMM) Expectation Maximization (EM) Principal Components Analysis (PCA) Independent Components Analysis (ICA) 13.2 Non-parametric models KNN Decision Tree Random Forest XG Boost |
| 第 14 週 | 14. Variational Inference EM Variants Variational Autoencoder Principal Components Analysis (PCA) |
| 第 15 週 | 15. Advanced topics To be determined Diffusion models |
| 第 16 週 | 16. Term project report |
1. Machine Learning with PyTorch and Scikit-Learn: Develop machine learning and deep learning models with Python, Sebastian Raschka, Packt Publishing, 2022-02-25 2. Probabilistic Machine Learning: An Introduction, Kevin P. Murphy, Summit Valley Press,2022-03-01 3. Probabilistic Machine Learning: Advanced Topics, Kevin P. Murphy, MIT,2023-08-15
- 地點
- online
- 時間
- on appointment
- 聯絡方式
- email: machingwen@ncyu.edu.tw