Bug#790803: ITP: neural -- machine-learning for atomistics

[Graham Inggs <graham@nerve.org.za>]

Package: wnpp
Severity: wishlist
Owner: Graham Inggs <graham@nerve.org.za>
X-Debbugs-CC: debian-devel@lists.debian.org

* Package name    : neural
  Version         : 1.0
  Upstream Author : Andrew Peterson, Alireza Khorshidi
* URL             : https://bitbucket.org/andrewpeterson/neural
* License         : GPL-3.0+
  Programming Lang: Python
  Description     : Machine Learning for Atomistics
 Neural is an open-source code designed to easily bring machine-learning to
 atomistic calculations. This allows one to predict (or really, interpolate)
 calculations on the potential energy surface, by optimizing a neural network
 representation of a "training set" of atomic images. The code works by
 learning from any other calculator (usually DFT) that can provide energy as
 a function of atomic coordinates. In theory, these predictions can take place
 with arbitrary accuracy approaching that of the original calculator.
 .
 Neural is designed to integrate closely with the Atomic Simulation
 Environment (ASE). As such, the interface is in pure python, although several
 compute-heavy parts of the underlying code also have fortran versions to
 accelerate the calculations. The close integration with ASE means that any
 calculator that works with ASE ─ including EMT, GPAW, DACAPO, VASP, NWChem,
 and Gaussian ─ can easily be used as the parent method.