Active learning in open experimental environments: selecting the right information channel(s) based on predictability in deep kernel learning
This addresses the challenge of optimizing experimental workflows in fields like materials science and chemistry, but appears incremental as it adapts existing methods to a specific scenario.
The paper tackles the problem of selecting the most predictive information channel in experimental settings with multiple modalities, using deep kernel learning for active learning in microscopy. It demonstrates applicability to automated synthesis and molecular systems, though no concrete performance numbers are provided.
Active learning methods are rapidly becoming the integral component of automated experiment workflows in imaging, materials synthesis, and computation. The distinctive aspect of many experimental scenarios is the presence of multiple information channels, including both the intrinsic modalities of the measurement system and the exogenous environment and noise signals. One of the key tasks in experimental studies is hence establishing which of these channels is predictive of the behaviors of interest. Here we explore the problem of discovery of the optimal predictive channel for structure-property relationships (in microscopy) using deep kernel learning for modality selection in an active experiment setting. We further pose that this approach can be directly applicable to similar active learning tasks in automated synthesis and the discovery of quantitative structure-activity relations in molecular systems.