
Atomic Convolutional Networks for Predicting ProteinLigand Binding Affinity
Empirical scoring functions based on either molecular force fields or ch...
read it

Simple and efficient algorithms for training machine learning potentials to force data
Abstract Machine learning models, trained on data from ab initio quantum...
read it

Efficient force field and energy emulation through partition of permutationally equivalent atoms
Kernel ridge regression (KRR) that satisfies energy conservation is a po...
read it

Neural Network Based in Silico Simulation of Combustion Reactions
Understanding and prediction of the chemical reactions are fundamental d...
read it

ForceNet: A Graph Neural Network for LargeScale Quantum Calculations
With massive amounts of atomic simulation data available, there is a hug...
read it

An Atomistic Machine Learning Package for Surface Science and Catalysis
We present work flows and a software module for machine learning model b...
read it

Detect the Interactions that Matter in Matter: Geometric Attention for ManyBody Systems
Attention mechanisms are developing into a viable alternative to convolu...
read it
Fast Neural Network Approach for Direct Covariant Forces Prediction in Complex MultiElement Extended Systems
Neural network force field (NNFF) is a method for performing regression on atomic structureforce relationships, bypassing expensive quantum mechanics calculation which prevents the execution of long abinitio quality molecular dynamics simulations. However, most NNFF methods for complex multielement atomic systems indirectly predict atomic force vectors by exploiting just atomic structure rotationinvariant features and the networkfeature spatial derivatives which are computationally expensive. We develop a staggered NNFF architecture exploiting both rotationinvariant and covariant features separately to directly predict atomic force vectors without using spatial derivatives, thereby reducing expensive structural feature calculation by 180480x. This acceleration enables us to develop NNFF which directly predicts atomic forces in complex ternary and quaternaryelement extended systems comprised of long polymer chains, amorphous oxide, and surface chemical reactions. The staggered rotationinvariantcovariant architecture described here can also directly predict complex covariant vector outputs from local physical structures in domains beyond computational material science.
READ FULL TEXT
Comments
There are no comments yet.