ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost
Abstract
We demonstrate how a deep neural network (NN) trained on a data set of quantum mechanical (QM) DFT calculated energies can learn an accurate and transferable atomistic potential for organic molecules containing H, C, N, and O atoms.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Jan 01, 2017
- Source ID
- 10.1039/c6sc05720a
Entities
People
- Adrian Roitberg
- Justin S Smith
- Olexandr Isayev
Organizations
- National Institute of General Medical Sciences
- National Science Foundation
- Office of Naval Research
- Office of Naval Research Global
- UNC Eshelman School of Pharmacy
- United States Department of Energy
- University of Florida
- University of North Carolina at Chapel Hill
- Yusuf Hamied Department of Chemistry