深度概率機器學習
Deep Probabilistic Machine Learning
| 節 | 週二 |
|---|---|
5 13:20–14:10 | 深度概率機器學習 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
Deep probabilistic machine learning is about making probabilistic predictions with deep neural networks, which can be appiled to generative AI sytems. This course focus on 1. providing reliable confidence scores for predictions in a systematic and analytical way, 2. generate probabilistic contents. The first part of this course covers Gaussian process regression, Gaussian process classifiers, deep Gaussian process classifiers and their applications, such as time series estimation and forecasting. We will study its financial applications. The second part of this course introduces some modern machine learning topics, especially generative AI systems, such as transformer networks, denoising diffusion, large language model, state space machines for sequence modeling etc.
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 URL = https://probml.github.io/pml-book/book2.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 (Coding and Report) Ex6. Integrating CNN and Gaussian process classifier. (Coding and report) Ex7. Transformer networks for object detection (Report) Ex8. Denoising Diffusion Models in computer vision (Report) Ex9. Large-Language Model (Report)
| 週次 | 主題 |
|---|---|
| 第 1 週 | Course outline |
| 第 2 週 | Reasoning under uncertainty Bayesian theorem |
| 第 3 週 | Monte Carlo sampling |
| 第 4 週 | Bayesian inference, Gaussian distribution and Gaussian process |
| 第 5 週 | Understanding kernels and similarity metrics |
| 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 | Towards Bayesian Neural network: Last-layer Laplace approximation vs. deterministic uncertainty estimation |
| 第 10 週 | Review and Report |
| 第 11 週 | Probabilistic classifier integrating deep neural network and Gaussian process (I) |
| 第 12 週 | Probabilistic classifier integrating deep neural network and Gaussian process (II) |
| 第 13 週 | Transformers Architecture Attention vs. State Space Models |
| 第 14 週 | Denoising Diffusion models |
| 第 15 週 | Vision-Language Pre-training (CLIP) Concepts disentangle representation |
| 第 16 週 | Term project report |
No textbook for this course.
- 地點
- on-line or 致遠樓 2樓R212)
- 時間
- By appointment
- 聯絡方式
- machingwen@nycu.edu.tw