https://github.com/machine-learning-tokyo/ml-math
Mathematics for Machine Learning
https://github.com/machine-learning-tokyo/ml-math
Last synced: 12 months ago
JSON representation
Mathematics for Machine Learning
- Host: GitHub
- URL: https://github.com/machine-learning-tokyo/ml-math
- Owner: Machine-Learning-Tokyo
- Created: 2020-01-18T03:41:56.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2020-09-15T20:51:37.000Z (over 5 years ago)
- Last Synced: 2025-04-18T16:27:00.042Z (about 1 year ago)
- Language: CSS
- Size: 3.41 MB
- Stars: 29
- Watchers: 7
- Forks: 5
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# ML-Math
This repository is part of our **MLT もくもく会 Math Reading Sessions** and the **MLT Mathematics for Machine Learning Discussions**.
# Review sessions and presentations
### [YouTube Playlist](https://www.meetup.com/Machine-Learning-Tokyo/events/270761078/)
- [Singular Value Decomposition](https://youtu.be/ONScfggC-M0) by [Jayson Cunanan, Ph.D.](https://www.linkedin.com/in/jayson-cunanan-phd/), AI Researcher/Engineer at AI inside 株式会社
- [Intro to Principal Component Analysis and Probabilistic PCA](https://www.youtube.com/watch?v=yyO08F5bFuA&list=PLaPdEEY26UXygpV-Cxch8Xkpl7IbFKBvK&index=5&t=0s) by [Hiroshi Urata, Data Scientist](https://www.linkedin.com/in/hiroshi-u/), Data Scientist, IBM Japan
- [Fourier transforms and a brief comparison with SVD](https://www.youtube.com/watch?v=8zRmr25vYBw&list=PLaPdEEY26UXygpV-Cxch8Xkpl7IbFKBvK&index=4&t=0s) by [Jayson Cunanan, Ph.D.](https://www.linkedin.com/in/jayson-cunanan-phd/), AI Researcher/Engineer at AI inside 株式会社
- [ML Math Review Session: Singular Value Decomposition](https://www.youtube.com/watch?v=PrIv-7SBTw8&list=PLaPdEEY26UXygpV-Cxch8Xkpl7IbFKBvK&index=3&t=0s) by [Emil Vatai](https://twitter.com/vatai), Postdoctoral Researcher, RIKEN, Japan (Review Chapter 4: Matrix Decompositions)
- [ML Math Review Session: Groups, residue classes](https://www.youtube.com/watch?v=nOxQ1vRt_p0&list=PLaPdEEY26UXygpV-Cxch8Xkpl7IbFKBvK&index=2&t=0s) by [Emil Vatai](https://twitter.com/vatai), Postdoctoral Researcher, RIKEN, Japan (Review Chapter 2: Linear Algebra)
- [ML Math Review Session: Gaussian Mixture Models](https://www.youtube.com/watch?v=2Tw0peN814k&t=10s) by [Pavitra Chakravarty](https://twitter.com/genomixgmailcom), Data Analyst, Converging Health, Dallas, TX USA (Review Chapter 11: Density Estimation with Gaussian Mixture Models)
# Reading sessions
Our [もくもく会 ML Math Reading Sessions](https://machinelearningtokyo.com/2019/11/28/ml-math-reading-sessions/) were based on "Mathematics For Machine Learning" by Marc Peter Deisenroth, A Aldo Faisal, and Cheng Soon Ong, to be published by Cambridge University Press. https://mml-book.github.io/
Sessions were held bi-weekly in different time zones on Sundays (PST, EST, GMT, CET, IST) and Mondays (APAC).
## Part I: Mathematical Foundations
- Introduction and Motivation
- Linear Algebra
- Analytic Geometry
- Matrix Decompositions
- Vector Calculus
- Probability and Distribution
- Continuous Optimization
## Part II: Central Machine Learning Problems
- When Models Meet Data
- Linear Regression
- Dimensionality Reduction with Principal Component Analysis
- Density Estimation with Gaussian Mixture Models
- Classification with Support Vector Machines