Jump to main content
Jump to site search

Issue 20, 2017
Previous Article Next Article

Energy landscapes for machine learning

Author affiliations

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

Back to tab navigation
Please wait while Download options loads

Publication details

The article was received on 19 Feb 2017, accepted on 20 Mar 2017 and first published on 03 Apr 2017


Article type: Perspective
DOI: 10.1039/C7CP01108C
Citation: Phys. Chem. Chem. Phys., 2017,19, 12585-12603
  •   Request permissions

    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

Search articles by author