機器學習
Machine Learning
| 節 | 週三 | 週五 |
|---|---|---|
2 09:00–09:50 | 機器學習 SA311（光復） | |
3 10:10–11:00 | 機器學習 SA311（光復） 2 節連堂 | |
4 11:10–12:00 |
* 根據陽明交大上課時間表所列
We plan to cover several topics including (but not limited to) supervised learning, deep learning, physics-informed neural networks, neural ordinary differential equations, unsupervised learning, diffusion maps.
Calculus, linear algebra, vector calculus, differential equations and python programming.
無備註
https://hackmd.io/@NYCUAM/2025ML
Homework assignments: 100%
教師未提供此項資料
| 週次 | 主題 |
|---|---|
| 第 1 週 | Supervised learning |
| 第 2 週 | MLE, MSE, LWLR |
| 第 3 週 | function approximation and classification loss |
| 第 4 週 | Logistic regression and Gaussian discriminant analysis |
| 第 5 週 | GDA and Generalized linear model |
| 第 6 週 | Neural networks as function representations |
| 第 7 週 | Score matching |
| 第 8 週 | SDE |
| 第 9 週 | Ito's lemma and Fokker Planck equation |
| 第 10 週 | Reverse SDE |
| 第 11 週 | Physics-informed neural networks and operator learning |
| 第 12 週 | least square regression and its application |
| 第 13 週 | Neural ODE |
| 第 14 週 | Unsupervised learning 1: PCA |
| 第 15 週 | Unsupervised learning 2: LLE, MDS |
| 第 16 週 | Unsupervised learning 3: diffusion maps |
教師未提供此項資料
- 地點
- 教師未提供此項資料
- 時間
- 教師未提供此項資料
- 聯絡方式
- 教師未提供此項資料