理论物理的机器学习
The course is targeted to those who know beginning graduate level physics but do not know machine learning. We will cover important methods in machine learning with a view to their applications to current physics such as string theory, particle physics, critical phenomena, gravitational waves and integrability. We will also cover some applications to Lie algebras. We will use Python3, scikit-learn and Keras/Tensorflow. These will be introduced in the lectures.
讲师
日期
2023年03月03日 至 04月28日
位置
| Weekday | Time | Venue | Online | ID | Password |
|---|---|---|---|---|---|
| 周一,周五 | 09:50 - 12:15 | A3-3-201 | ZOOM 03 | 242 742 6089 | BIMSA |
修课要求
Elementary multivariate calculus, elementary statistics. Some basic General Relativity and Statistical Mechanics may help in following the applications.
课程大纲
1. Linear Regression and Generalized Linear Models
2. Logistic Regression
3. Constructing and Validating Models: Bias, Variance and Validation
4. K nearest neighbours, Classification and Regression
5. Decision Trees
6. Boosting and Bagging, Boosted Trees.
7. Support Vector Machines
8. Neural Networks, Multi-Layer Perceptrons
9. Convolutional Neural Networks
10. Unsupervised Learning: Clustering, Dimensionality Reduction
11. Generative Models
2. Logistic Regression
3. Constructing and Validating Models: Bias, Variance and Validation
4. K nearest neighbours, Classification and Regression
5. Decision Trees
6. Boosting and Bagging, Boosted Trees.
7. Support Vector Machines
8. Neural Networks, Multi-Layer Perceptrons
9. Convolutional Neural Networks
10. Unsupervised Learning: Clustering, Dimensionality Reduction
11. Generative Models
听众
Undergraduate
, Graduate
视频公开
不公开
笔记公开
不公开
语言
英文
讲师介绍
Shailesh Lal于Harish Chandra研究所获得博士学位。他的研究兴趣是机器学习在弦理论和数学物理中的应用，弦理论中的黑洞和higher-spin holography。