Open Problem: Active Representation Learning
This work addresses the challenge of enhancing data collection and model efficiency in scientific domains like microscopy, though it is incremental as it extends existing active SLAM concepts.
The paper introduces Active Representation Learning, a novel problem class combining exploration and representation learning in partially observable environments, aiming to improve data collection and model building efficiency in scientific discovery, exemplified by adaptive microscopy.
In this work, we introduce the concept of Active Representation Learning, a novel class of problems that intertwines exploration and representation learning within partially observable environments. We extend ideas from Active Simultaneous Localization and Mapping (active SLAM), and translate them to scientific discovery problems, exemplified by adaptive microscopy. We explore the need for a framework that derives exploration skills from representations that are in some sense actionable, aiming to enhance the efficiency and effectiveness of data collection and model building in the natural sciences.