Issue 20, 2017

Energy landscapes for machine learning

Abstract

Machine learning techniques are being increasingly used as flexible non-linear fitting and prediction tools in the physical sciences. Fitting functions that exhibit multiple solutions as local minima can be analysed in terms of the corresponding machine learning landscape. Methods to explore and visualise molecular potential energy landscapes can be applied to these machine learning landscapes to gain new insight into the solution space involved in training and the nature of the corresponding predictions. In particular, we can define quantities analogous to molecular structure, thermodynamics, and kinetics, and relate these emergent properties to the structure of the underlying landscape. This Perspective aims to describe these analogies with examples from recent applications, and suggest avenues for new interdisciplinary research.

Graphical abstract: Energy landscapes for machine learning

Article information

Article type
Perspective
Submitted
19 Feb 2017
Accepted
20 Mar 2017
First published
03 Apr 2017
This article is Open Access
Creative Commons BY license

Phys. Chem. Chem. Phys., 2017,19, 12585-12603

Energy landscapes for machine learning

A. J. Ballard, R. Das, S. Martiniani, D. Mehta, L. Sagun, J. D. Stevenson and D. J. Wales, Phys. Chem. Chem. Phys., 2017, 19, 12585 DOI: 10.1039/C7CP01108C

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence. You can use material from this article in other publications without requesting further permissions from the RSC, provided that the correct acknowledgement is given.

Read more about how to correctly acknowledge RSC content.

Social activity

Spotlight

Advertisements