Back to Search
Start Over
Stochastic Neural Network Approach for Learning High-Dimensional Free Energy Surfaces.
- Source :
-
Physical review letters [Phys Rev Lett] 2017 Oct 13; Vol. 119 (15), pp. 150601. Date of Electronic Publication: 2017 Oct 11. - Publication Year :
- 2017
-
Abstract
- The generation of free energy landscapes corresponding to conformational equilibria in complex molecular systems remains a significant computational challenge. Adding to this challenge is the need to represent, store, and manipulate the often high-dimensional surfaces that result from rare-event sampling approaches employed to compute them. In this Letter, we propose the use of artificial neural networks as a solution to these issues. Using specific examples, we discuss network training using enhanced-sampling methods and the use of the networks in the calculation of ensemble averages.
Details
- Language :
- English
- ISSN :
- 1079-7114
- Volume :
- 119
- Issue :
- 15
- Database :
- MEDLINE
- Journal :
- Physical review letters
- Publication Type :
- Academic Journal
- Accession number :
- 29077427
- Full Text :
- https://doi.org/10.1103/PhysRevLett.119.150601