Nature Communications (Sep 2020)

Machine learning identifies scale-free properties in disordered materials

  • Sunkyu Yu,
  • Xianji Piao,
  • Namkyoo Park

DOI
https://doi.org/10.1038/s41467-020-18653-9
Journal volume & issue
Vol. 11, no. 1
pp. 1 – 11

Abstract

Read online

The performance of a trained neural network may be biased even by generic features of its architecture. Yu et al. ask for the disordered lattice of atoms producing a certain wave localization and the network prefers to answer with power-law distributed displacements.