Machine Learning Force Fields
Oliver T. Unke, Stefan Chmiela, Huziel E. Sauceda et al. · Chemical Reviews · 2021
methods and the efficiency of classical FFs. The key idea is to learn the statistical relation between chemical structure and potential energy without relying on a preconceived notion of fixed chemical bonds or knowledge about the relevant interactions. Such universal ML approximations are in principle only limited by the quality and quantity of the reference data used to train them. This review gives an overview of applications of ML-FFs and the chemical insights that can be obtained from them. The core concepts underlying ML-FFs are described in detail, and a step-by-step guide for constructing and testing them from scratch is given. The text concludes with a discussion of the challenges that remain to be overcome by the next generation of ML-FFs.
Cited by 1,584 works. doi:10.1021/acs.chemrev.0c01111
Authors
- Oliver T. Unke
- Stefan Chmiela
- Huziel E. Sauceda
- Michael Gastegger
- Igor Poltavsky
- Kristof T. Schütt
- Alexandre Tkatchenko
- Klaus‐Robert Müller
References
- The Nature of Statistical Learning Theory
- Generalized Gradient Approximation Made Simple
- Support-Vector Networks
- Deep learning
- AutoResearch Lite: a reproducible paper-inspired experiment runner (Adam mechanism reproduction and convergence-speed comparison)
- Neural networks for pattern recognition
- Dropout: a simple way to prevent neural networks from overfitting
- A logical calculus of the ideas immanent in nervous activity
- A training algorithm for optimal margin classifiers
- Rectified Linear Units Improve Restricted Boltzmann Machines