# PANNA: Properties from Artificial Neural Network Architectures

## TL;DR

PANNA is a versatile software toolkit that leverages neural networks and TensorFlow to efficiently predict material properties from atomistic data, integrating with molecular dynamics simulations.

## Contribution

It introduces a comprehensive, flexible framework for creating neural network models tailored to atomistic systems, including data handling, descriptor building, and force-field generation.

## Key findings

- Supports multiple neural network architectures and activation functions.
- Enables use on various hardware platforms including CPU, GPU, and TPU.
- Facilitates large dataset modeling for material property prediction.

## Abstract

Prediction of material properties from first principles is often a computationally expensive task. Recently, artificial neural networks and other machine learning approaches have been successfully employed to obtain accurate models at a low computational cost by leveraging existing example data. Here, we present a software package "Properties from Artificial Neural Network Architectures" (PANNA) that provides a comprehensive toolkit for creating neural network models for atomistic systems. Besides the core routines for neural network training, it includes data parser, descriptor builder and force-field generator suitable for integration within molecular dynamics packages. PANNA offers a variety of activation and cost functions, regularization methods, as well as the possibility of using fully-connected networks with custom size for each atomic species. PANNA benefits from the optimization and hardware-flexibility of the underlying TensorFlow engine which allows it to be used on multiple CPU/GPU/TPU systems, making it possible to develop and optimize neural network models based on large datasets.