Amp: Atomistic Machine-learning Potentials

Welcome to Amp documentation! This project is being developed at Brown University in the School of Engineering, primarily by Andrew Peterson and Alireza Khorshidi, and is released under the GNU General Public License. This is a relatively new project, so things are constantly changing!

(Note that Amp is built off of our previous project, Neural. You may still find Neural at our bitbucket page.)

Table of Contents:

• Introduction
• Installation
  • Install ASE
  • Check out the code
  • Set the environment
  • Recommended step: Fortran modules
  • Recommended step: Run the tests
• How to use Amp?
  • Initializing Amp
  • Starting from old parameters
  • Training Amp
  • Growing your train set
  • Using trained Amp
  • Complete example
• Theory
  • Atomic representation of potential energy
  • Descriptor
  • Regression Model
• Parallel Computing
• Development
  • Repositories and branching
  • Contributing
  • Documentation

List of All Methods:

• Main
• Descriptor
• Regression
• Utilities
• Analysis

Indices and tables

• Index
• Module Index
• Search Page