Ensemble learning and iterative training (ELIT) machine learning: applications towards uncertainty quantification and automated experiment in atom-resolved microscopy

TL;DR

This paper introduces an ensemble learning and iterative training framework for deep learning in atom-resolved electron microscopy, enhancing feature detection, uncertainty quantification, and enabling automated experiments despite out-of-distribution data shifts.

Contribution

The paper presents a novel ensemble learning and iterative training workflow that improves deep learning robustness and automation in atom-resolved microscopy applications.

Findings

Enhanced feature detection accuracy in electron microscopy images.

Effective uncertainty quantification in deep learning analysis.

Automated adaptation to imaging condition variations without human retraining.

Abstract

Deep learning has emerged as a technique of choice for rapid feature extraction across imaging disciplines, allowing rapid conversion of the data streams to spatial or spatiotemporal arrays of features of interest. However, applications of deep learning in experimental domains are often limited by the out-of-distribution drift between the experiments, where the network trained for one set of imaging conditions becomes sub-optimal for different ones. This limitation is particularly stringent in the quest to have an automated experiment setting, where retraining or transfer learning becomes impractical due to the need for human intervention and associated latencies. Here we explore the reproducibility of deep learning for feature extraction in atom-resolved electron microscopy and introduce workflows based on ensemble learning and iterative training to greatly improve feature detection. This approach both allows incorporating uncertainty quantification into the deep learning analysis and also enables rapid automated experimental workflows where retraining of the network to compensate for out-of-distribution drift due to subtle change in imaging conditions is substituted for a human operator or programmatic selection of networks from the ensemble. This methodology can be further applied to machine learning workflows in other imaging areas including optical and chemical imaging.