概率機器學習與類神經網路
Probabilistic Machine Learning and Neural Networks
| 節 | 週三 |
|---|---|
5 13:20–14:10 | 概率機器學習與類神經網路 CM217 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
Probabilistic machine learning is about making probabilistic predictions. It’s like providing confidence scores for predictions in a systematic and analytical way. The first part of this course covers Gaussian process regression, Gaussian process classifiers, and their applications, such as time series estimation and forecasting. We will also study financial applications. The second part of this course introduces some modern neural networks, such as Transformer with shifted windows, dynamic head with attentions, and teacher-student frameworks. The lecture will be delivered in Mandarin. (中文授課) 我們使用Microsoft Teams教學,網址如下 https://tinyurl.com/kch4sfey
1. Basic machine learning concepts, such as overfitting, underlining, gradient descent, etc.. 2. Basics of probability theory, linear algebra, and multivariable calculus 3. Reasonably computer programming skills in Python/numpy
Websites and reference books. 1. Hennig, P., 2020. Probabilistic Machine Learning. lecture course, University of Tübingen, URL = https://uni-tuebingen.de/en/180804 2. Kevin P. Murphy, Probabilistic Machine Learning: An introduction, MIT Press, 2022, URL = https://probml.github.io/pml-book/book1.html
Ex1. Basic Bayesian inference. (Coding) Ex2. Gaussian linear regression (Coding) Ex3. Gaussian process regression (Coding) Ex4. Integrating Gaussian process classifier and deep neural networks. (Coding) Ex5. Financial Application of Gaussian processes and Bayesian optimization (Report) Ex6. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (Report) Ex7. Dynamic Head: Unifying Object Detection Heads with Attentions (Report) Ex8. Teacher-student framework (Report) Ex9. Integrating Gaussian process classifier and Swin transformer. (Coding and report)
| 週次 | 主題 |
|---|---|
| 第 1 週 | Course outline |
| 第 2 週 | Reasoning under uncertainty |
| 第 3 週 | Monte Carlo sampling |
| 第 4 週 | Gaussian distribution and Gaussian process |
| 第 5 週 | Understanding Kernels |
| 第 6 週 | Example: Financial Application of Gaussian processes |
| 第 7 週 | Gaussian process classification |
| 第 8 週 | Generalized linear model and Exponential families |
| 第 9 週 | Example: Last-layer Laplace approximation |
| 第 10 週 | Review and Report |
| 第 11 週 | Vision Transformers |
| 第 12 週 | Swin Transformer |
| 第 13 週 | Dynamic Head: Unifying Object Detection Heads with Attentions |
| 第 14 週 | Teacher-student framework |
| 第 15 週 | Integrating Gaussian process classifier and Swin transformer. |
| 第 16 週 | Term project report |
No textbook for this course.
- 時間
- By appointment
- 聯絡方式
- machingwen@nycu.edu.tw