Machine-Learning

in Physics

A few words about the course

Machine-learning and deep-learning has attracted a lot of attention in the past few years in the scientific community. Everyday there are new discoveries and inventions that exploit machine-learning technique one way or another. The objective of this course is present the basics of machine-learning with a focus on neural networks and deep-learning. The course is going to be hands-on and involves doing a couple of projects. Preferably, projects are to be related to the research that students are involved in. For more information, see the course syllabus .

Course Materials

Github page

All the course material, including the course notes and jupyter notebooks are available at the new github page.

The Github page from Winter 2019

You can find the material from last year in this page. Some of the libraries has been updated since last year and as a result, the codes may not be functional anymore. Also the syllabus has changed since last year. For the updated lectures, please see the updated github repository.

Resources

Here's a list of books and materials that could be helpful for this course. We may add more material as we proceed.

“A high-bias, low-variance introduction to Machine Learning for physicists”

Review article by Pankaj Mehta et al.

The article is available on arxiv .

Neural Networks and Deep Learning

By Michael Nielsen

This book is available on-line.

Machine Learning course on Coursera

by Andrew Ng

This is the seminal course (and probably th most famous one) on the basics of machine-learning. It gives great introduction to machine-learning and it would be great if you could go through the lectures before we start our course. You can find the course here.