可信任與節能機器學習
Trustworthy and Green Machine Learning
| 節 | 週二 |
|---|---|
5 13:20–14:10 | 可信任與節能機器學習 CM215（歸仁） 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
This course consists of two parts: trustworthy machine learning algorithms and efficient algorithm development and implementation. In the first part, we will discuss algorithms that provide reliable confidence scores for their predictions in a systematic and analytical manner, including Gaussian Process regression and classification. In the second part, we will explore efficient accelerated computation, covering training, fine-tuning, and inference of large language models on consumer-grade computers.
Basic machine learning concepts, such as overfitting, gradient descent, neural networks etc..
無備註
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
Homework: 30% Project: 50% Attendance: 20% 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) Ex6. Integrating CNN and Gaussian process classifier. (Coding and report) Ex7. Memory-efficient LLM Training with GaLore (Coding and Report) Ex8. Memory-efficient LLM Training with PowerInfer (Coding and Report)
教師未提供此項資料
| 週次 | 主題 |
|---|---|
| 第 1 週 | Course outline 2025-02-18(二) 時數：[2025-02-18]馬清文(3.00) |
| 第 2 週 | Reasoning under uncertainty Bayesian theorem 2025-02-25(二) 時數：[2025-02-25]馬清文(3.00) |
| 第 3 週 | Monte Carlo sampling 2025-03-04(二) 時數：[2025-03-04]馬清文(3.00) |
| 第 4 週 | Bayesian inference, Gaussian distribution and Gaussian process 2025-03-11(二) 時數：[2025-03-11]馬清文(3.00) |
| 第 5 週 | Understanding kernels and similarity metrics 2025-03-18(二) 時數：[2025-03-18]馬清文(3.00) |
| 第 6 週 | Example: Financial Application of Gaussian processes 2025-03-25(二) 時數：[2025-03-25]馬清文(3.00) |
| 第 7 週 | Gaussian process classification 2025-04-01(二) 時數：[2025-04-01]馬清文(3.00) |
| 第 8 週 | Generalized linear model and Exponential families 2025-04-08(二) 時數：[2025-04-08]馬清文(3.00) |
| 第 9 週 | Towards Bayesian Neural network: Last-layer Laplace approximation vs. deterministic uncertainty estimation 2025-04-15(二) 時數：[2025-04-15]馬清文(3.00) |
| 第 10 週 | Review and Report 2025-04-22(二) 時數：[2025-04-22]馬清文(3.00) |
| 第 11 週 | Probabilistic classifier integrating deep neural network and Gaussian process (I) 2025-04-29(二) 時數：[2025-04-29]馬清文(3.00) |
| 第 12 週 | Probabilistic classifier integrating deep neural network and Gaussian process (II) 2025-05-06(二) 時數：[2025-05-06]馬清文(3.00) |
| 第 13 週 | Memory-efficient LLM Training 2025-05-13(二) 時數：[2025-05-13]馬清文(3.00) |
| 第 14 週 | Memory-efficient LLM Inference 2025-05-20(二) 時數：[2025-05-20]馬清文(3.00) |
| 第 15 週 | Large Foundation models 2025-05-27(二) 時數：[2025-05-27]馬清文(3.00) |
| 第 16 週 | Term project report 2025-06-03(二) 時數：[2025-06-03]馬清文(3.00) |
No textbook for this course. Pioneering and contemporary papers will be discussed in the class.
- 地點
- in the class
- 時間
- By appointment or after class every week.
- 聯絡方式
- machingwen@nycu.edu.tw