Online Course: Machine Learning for Physicists 2020
This site contains all the lectures and material of the Online Course: Machine Learning for Physicists 2020 taught at the physics department of the university in Erlangen (Bavaria/Germany).
This course is taught by Florian Marquardt (PhD), a theoretical physicist working at the intersection of nanophysics and quantum optics, with a strong recent focus on applications of machine learning. His group is located at the Max Planck Institute for the Science of Light, and he is also affiliated with the university in Erlangen.
The original website for the course is https://machine-learning-for-physicists.org, but the detailed up-to-date materials for the 2020 online version will be found on this version of the website!
Some of the questions that will be addressed in this lecture series
- How do artificial neural networks look like?
- How do you train them efficiently?
- How do you recognize images?
- How do you learn a compact representation of data, without providing any extra information?
- How do you analyze time series and sentences?
- How do you discover strategies from scratch without a teacher?
- What are some modern applications in science/physics?
First of all, you want to install the Python programming language. Also, Florian recommends JupyterLab as a convenient notebook interface for python programming. Depending on your taste and your system, you might want to download these individually or as part of a full distribution like Anaconda.
An alternative, completely online solution is the Colaboratory platform by Google. This is a web-based jupyter notebook interface to python that comes with TensorFlow & Keras pre-installed and allows you to run your code for free on their GPU servers.
Starting in the 3rd lecture, we will use Keras, the convenient high-level python neural-network software package. This is included automatically in every recent TensorFlow installation, so Florian recommends installing TensorFlow (after having python) and then getting access to Keras commands in the form:
import tensorflow as tf
from tensorflow.keras.layers import Dense
I provide a third option to run the contents using Mybinder. To run the contents you can simply click the following button. This will create a container with all the needed packages.
