paper-with-me

홈 › Papers

FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentials

2024-05-02 · Thomas Plé, Olivier Adjoua, Louis Lagardère, Jean-Philip Piquemal

Neural network interatomic potentials (NNPs) have recently proven to be powerful tools to accurately model complex molecular systems while bypassing the high numerical cost of ab-initio molecular dynamics simulations. In recent years, numerous advances in model architectures as well as the development of hybrid models combining machine-learning (ML) with more traditional, physically-motivated, force-field interactions have considerably increased the design space of ML potentials. In this paper, we present FeNNol, a new library for building, training and running force-field-enhanced neural network potentials. It provides a flexible and modular system for building hybrid models, allowing to easily combine state-of-the-art embeddings with ML-parameterized physical interaction terms without the need for explicit programming. Furthermore, FeNNol leverages the automatic differentiation and just-in-time compilation features of the Jax Python library to enable fast evaluation of NNPs, shrinking the performance gap between ML potentials and standard force-fields. This is demonstrated with the popular ANI-2x model reaching simulation speeds nearly on par with the AMOEBA polarizable force-field on commodity GPUs (GPU=Graphics processing unit). We hope that FeNNol will facilitate the development and application of new hybrid NNP architectures for a wide range of molecular simulation problems.

📄 PDF Abstract BibTeX arXiv:2405.01491

Code (1)

thomasple/FeNNol 공식 구현 jax

Tasks

GPU

Methods 이 논문이 사용한 방법론

Library 설명 없음

Similar Papers 제목 키워드 기반

TorchRL: A data-driven decision-making library for PyTorch

2023-06-01 · Albert Bou, Matteo Bettini, Sebastian Dittert, Vikash Kumar 외

PyTorch has ascended as a premier machine learning framework, yet it lacks a native and comprehensive library for decision and control tasks suitable for large development teams dealing with complex real-world data and e…

Computational EfficiencyDecision MakingReinforcement Learning (RL)

BayesOpt: A Bayesian Optimization Library for Nonlinear Optimization, Experimental Design and Bandits

2014-05-29 · Ruben Martinez-Cantin

BayesOpt is a library with state-of-the-art Bayesian optimization methods to solve nonlinear optimization, stochastic bandits or sequential experimental design problems. Bayesian optimization is sample efficient by build…

Bayesian OptimizationExperimental DesignHyperparameter Optimization

RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup

2023-10-20 · Nico Bohlinger, Klaus Dorer

This paper presents the new Deep Reinforcement Learning (DRL) library RL-X and its application to the RoboCup Soccer Simulation 3D League and classic DRL benchmarks. RL-X provides a flexible and easy-to-extend codebase w…

Deep Reinforcement Learningreinforcement-learningReinforcement Learning

Salesforce CausalAI Library: A Fast and Scalable Framework for Causal Analysis of Time Series and Tabular Data

2023-01-25 · Devansh Arpit, Matthew Fernandez, Itai Feigenbaum, Weiran Yao 외

We introduce the Salesforce CausalAI Library, an open-source library for causal analysis using observational data. It supports causal discovery and causal inference for tabular and time series data, of discrete, continuo…

Causal DiscoveryCausal InferenceTime SeriesTime Series Analysis

BuildingGym: An open-source toolbox for AI-based building energy management using reinforcement learning

2025-09-15 · Xilei Dai, Ruotian Chen, Songze Guan, Wen-Tai Li 외 arxiv

Reinforcement learning (RL) has proven effective for AI-based building energy management. However, there is a lack of flexible framework to implement RL across various control problems in building energy management. To a…

Reinforcement Learning