Machine learning in a data-limited regime: Augmenting experiments with synthetic data uncovers order in crumpled sheets

Jordan Hoffmann, Yohai Bar-Sinai, Lisa M. Lee, Jovana Andrejevic, Shruti Mishra, Shmuel M. Rubinstein, Chris H. Rycroft

Research output: Contribution to journalArticlepeer-review

Abstract

Machine learning has gained widespread attention as a powerful tool to identify structure in complex, highdimensional data. However, these techniques are ostensibly inapplicable for experimental systems where data are scarce or expensive to obtain. Here, we introduce a strategy to resolve this impasse by augmenting the experimental dataset with synthetically generated data of a much simpler sister system. Specifically, we study spontaneously emerging local order in crease networks of crumpled thin sheets, a paradigmatic example of spatial complexity, and show that machine learning techniques can be effective even in a data-limited regime. This is achieved by augmenting the scarce experimental dataset with inexhaustible amounts of simulated data of rigid flat-folded sheets, which are simple to simulate and share common statistical properties. This considerably improves the predictive power in a test problem of pattern completion and demonstrates the usefulness of machine learning in bench-top experiments where data are good but scarce.

Original languageEnglish
Article numbereaau6792
JournalScience advances
Volume5
Issue number4
DOIs
StatePublished - 2019
Externally publishedYes

Fingerprint

Dive into the research topics of 'Machine learning in a data-limited regime: Augmenting experiments with synthetic data uncovers order in crumpled sheets'. Together they form a unique fingerprint.

Cite this