Problem-fluent models for complex decision-making in autonomous materials research

Abstract

We review our recent work in the area of autonomous materials research, highlighting the coupling of machine learning methods and models and more problem-aware modeling. We review the general Bayesian framework for closed-loop design employed by many autonomous materials platforms. We then provide examples of our work on such platforms. We finally review our approaches to extend current statistical and ML models to better reflect problem-specific structure including the use of physics-based models and incorporation of operational considerations into the decision-making procedure.

arXiv commentTo be published in Computational Materials Science

References in corpus (10)

• Practical Bayesian Optimization of Machine Learning Algorithms
• On-the-fly Closed-loop Autonomous Materials Discovery via Bayesian Active Learning
• Search for the QCD Critical Point with Fluctuations of Conserved Quantities in Relativistic Heavy-Ion Collisions at RHIC : An Overview
• A Tutorial on Bayesian Optimization
• Higher Moments of Net-proton Multiplicity Distributions at RHIC
• Active Learning with Statistical Models
• Skewness and kurtosis of net baryon-number distributions at small values of the baryon chemical potential
• A unified model of droplet epitaxy for compound semiconductor nanostructures: experiments and theory
• Practical Multi-fidelity Bayesian Optimization for Hyperparameter Tuning
• Higher Moments of Net-Particle Multiplicity Distributions