Hypothesis Learning in Automated Experiment: Application to Combinatorial Materials Libraries
1 MIN READ

Hypothesis Learning in Automated Experiment: Application to Combinatorial Materials Libraries

Hypothesis Learning in Automated Experiment: Application to Combinatorial Materials Libraries
(a) The “automated scientist” concept based on hypothesis learning. (b) Hysteresis loops of Sm-BiFeO3 with different Sm ratio obtained in band excitation piezoresponse spectroscopy measurements. (c) Predictions of the model that received the highest reward.

Scientific Achievement

An active learning approach based on co-navigation of the hypothesis and experimental spaces is developed.

Significance and Impact

This approach, actively testing alternative hypotheses during an experiment, can extend to higher-dimensional parameter spaces and more complex physical problems once the experimental workflow and hypothesis-generation mechanism are available.

Research Details

  • Hypothesis-learning is realized via a combination of fully Bayesian structured Gaussian processes and reinforcement learning policy refinement
  • Hypothesis-learning with Piezoresponse Force Microscopy is used for exploring concentration-induced phase transitions in combinatorial libraries of Sm-doped BiFeO3.

M. Ziatdinov, Y. Liu, A.N. Morozovska, E.A. Eliseev, X. Zhang, I. Takeuchi, and S.V. Kalinin, Advanced Materials (2022). DOI: 10.1002/adma.202201345

Related Researchers