Pythonic Machine Learning
We will code machine learning solutions for various datasets including Graphs, Images and Sequences. The emphasis will strongly be on developing robust code and other best practices.
Lecturer
Date
25th February ~ 27th May, 2025
Location
| Weekday | Time | Venue | Online | ID | Password |
|---|---|---|---|---|---|
| Tuesday | 09:50 - 11:25 | A3-3-301 | ZOOM 05 | 293 812 9202 | BIMSA |
| Tuesday | 13:30 - 15:05 | A3-3-301 | ZOOM 05 | 293 812 9202 | BIMSA |
Prerequisite
A background in statistics/mathematics/physics
Syllabus
1. Basic Python, Data types, File handling, Vectorization
2. Object Oriented Programming, Inheritance
3. Machine Learning an introductory dataset, evaluations and pitfalls
4. The underlying theory
5. Machine Learning with best practices (models, bias/variance, performance metrics, inference)
6. Unsupervised Learning
7. Machine Learning on Graphs
8. Deep Learning
2. Object Oriented Programming, Inheritance
3. Machine Learning an introductory dataset, evaluations and pitfalls
4. The underlying theory
5. Machine Learning with best practices (models, bias/variance, performance metrics, inference)
6. Unsupervised Learning
7. Machine Learning on Graphs
8. Deep Learning
Audience
Advanced Undergraduate
, Graduate
, Postdoc
Video Public
Yes
Notes Public
Yes
Language
English
Lecturer Intro
Dr Shailesh Lal received his PhD from the Harish-Chandra Research Institute. His research interests are applications of machine learning to string theory and mathematical physics, black holes in string theory and higher-spin holography.