Guardado en:
Detalles Bibliográficos
Autores principales: Milosevic, Nikola, Müller, Gesine, Huisken, Jan, Scherf, Nico
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2406.03845
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929578334748672
author Milosevic, Nikola
Müller, Gesine
Huisken, Jan
Scherf, Nico
author_facet Milosevic, Nikola
Müller, Gesine
Huisken, Jan
Scherf, Nico
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_03845
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Open Problem: Active Representation Learning
Milosevic, Nikola
Müller, Gesine
Huisken, Jan
Scherf, Nico
Machine Learning
Robotics
Systems and Control
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.
title Open Problem: Active Representation Learning
topic Machine Learning
Robotics
Systems and Control
url https://arxiv.org/abs/2406.03845