4. Tutorials: Machine Learning Potentials

These tutorials show how to use Task MachineLearning, in which parameters of machine learning potentials are fitted.

Other AMS tutorials (not using ParAMS) can be found in the Tutorials section of the main AMS documentation.

We recommend all ParAMS users to go through the Getting Started: Lennard-Jones tutorial before any other tutorial.

• 4.1. Train M3GNet with the ParAMS GUI
• 4.2. Train M3GNet with Python
• 4.3. Python ML: PES Scans and Geometry Optimization jobs in the “Test set”
• 4.4. Convert between ParAMS and ASE formats

See also

Simple Active Learning for automatic data generation and parametrization