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

Abstract

Machine learning has gained widespread attention as a powerful tool to identify structure in complex, high-dimensional data. However, these techniques are ostensibly inapplicable for experimental systems where data is 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 significantly improves the predictive power in a test problem of pattern completion and demonstrates the usefulness of machine learning in bench-top experiments where data is good but scarce.

arXiv comment8 pages, 5 figures (+ Supplemental Materials: 5 pages, 6 figures)

References in corpus (13)

• Playing Atari with Deep Reinforcement Learning
• Axiomatic Attribution for Deep Networks
• Machine learning phases of matter
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Identifying structural flow defects in disordered solids using machine learning methods
• Machine learning quantum phases of matter beyond the fermion sign problem
• Distilling a Neural Network Into a Soft Decision Tree
• Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning
• Embedding Projector: Interactive Visualization and Interpretation of Embeddings
• The Relationship Between Local Structure and Relaxation in Out-of-Equilibrium Glassy Systems
• Disconnecting structure and dynamics in glassy thin films
• Ridge Network in Crumpled Paper
• The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities

Cited by in corpus (10)

• Physics-enhanced deep surrogates for partial differential equations
• Machine Learning of Implicit Combinatorial Rules in Mechanical Metamaterials
• Soft Metamaterials: Adaptation and Intelligence
• A model for the fragmentation kinetics of crumpled thin sheets
• Power-law Scaling to Assist with Key Challenges in Artificial Intelligence
• Machine learning depinning of dislocation pileups
• Simulation of crumpled sheets via alternating quasistatic and dynamic representations
• Brain experiments imply adaptation mechanisms which outperform common AI learning algorithms
• Packing of elastic rings with friction
• Beyond Quality and Quantity: Contact Distribution Encodes Frictional Strength