Code to go along the 2021/22 lecture course "Advanced Machine Learning for Physics, Science, and Artificial Scientific Discovery". See the website of the course, https://pad.gwdg.de/s/2021_AdvancedMachineLearningForScience !
We will use python (the programming language) and tensorflow (the neural-network / automatic differentiation package).
Free web platforms for python and tensorflow:
If you do not want to bother with installing things, you can do everything online, by using Google Colab, https://colab.research.google.com/notebooks/welcome.ipynb, or Deepnote, https://deepnote.com/. Both of these platforms offer an online jupyter notebook environment where you can directly run python and tensorflow on their servers (including GPU support to some extent). Deepnote is particularly nice if several people want to access the same calculation at the same time from different computers. You could download notebooks from here and then upload them into either of these platforms and play around.
Local installation on your computer:
First install https://www.python.org/ (for convenience, you might install it as part of a bigger package, like conda, https://docs.conda.io/en/latest/miniconda.html). Then go to https://www.tensorflow.org/ to install tensorflow for free (once you have python installed, this can be simply down by using the python package manager pip: use 'pip install tensorflow' in a Terminal; possibly you want to do 'pip install --upgrade pip' before).