Skip to content

dsl-unibe-ch/Mathematical-Methods-for-ML-and-AI

 
 

Repository files navigation

Binder

Open In Colab

Self-study course for Mathematics Methods

Overview

This course creates a bridge between theoretical knowledge and practical application, opening up a new dimension of thinking. POarticipants will develop new mathematical intuitions by contextualizing theoretical questions within practical scenarios. Additionally, the course emphasizes how mathematical skills enhance the understanding and application of machine learning solutions.

Objective

The aim of this module is to remodel your mathematical knowledge by shifting the focus from abstract mathematics to mathematics with a specific purpose. This shift equips you for a deeper dive into machine learning, enhancing your ability to interpret results and optimize models.

Organisation

This is a 3-day-course that you can do on your own at home before the CAS starts. If you have questions regarding the exercises or something theoretical, join the Q&A sessions on the dates listed below. Please provide your questions beforehand via Ilias.

  • Q&A session:
    13 August 2025, 16-18 o'clock or
    15 August 2025, 16-18 o'clock.

    Location: Online via Zoom, link is provided on Ilias

Course Material

The course material is organized in Jupyter notebooks using Python as the primary programming language. This setup provides a hands-on approach to learning, allowing you to directly apply mathematical concepts within a practical framework.

Licence

This material, in whole or in part, may be:

  • Distributed
  • Remixed
  • Adapted
  • Built upon

These activities are permitted for noncommercial purposes only, under the following conditions:

  • Attribution: You must provide appropriate credit to the creator, Kinga Sipos. Please link to the online module as a reference.
  • ShareAlike: If you remix, adapt, or build upon the material, you must license your contributions under the identical terms.

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. For more details, see Creative Commons License.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 99.8%
  • Python 0.2%