Supervised Learning in Physical Networks: From Machine Learning to Learning Machines

Materials and machines are often designed with particular goals in mind, so that they exhibit desired responses to given forces or constraints. Here we explore an alternative approach, namely physical coupled learning. In this paradigm, the system is not initially designed to accomplish a task, but...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Menachem Stern, Daniel Hexner, Jason W. Rocks, Andrea J. Liu
Formato:	article
Lenguaje:	EN
Publicado:	American Physical Society 2021
Materias:	Physics QC1-999
Acceso en línea:	https://doaj.org/article/bfdef93505ef4ccea0370881623d513f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bfdef93505ef4ccea0370881623d513f
record_format	dspace
spelling	oai:doaj.org-article:bfdef93505ef4ccea0370881623d513f2021-12-02T15:46:52ZSupervised Learning in Physical Networks: From Machine Learning to Learning Machines10.1103/PhysRevX.11.0210452160-3308https://doaj.org/article/bfdef93505ef4ccea0370881623d513f2021-05-01T00:00:00Zhttp://doi.org/10.1103/PhysRevX.11.021045http://doi.org/10.1103/PhysRevX.11.021045https://doaj.org/toc/2160-3308Materials and machines are often designed with particular goals in mind, so that they exhibit desired responses to given forces or constraints. Here we explore an alternative approach, namely physical coupled learning. In this paradigm, the system is not initially designed to accomplish a task, but physically adapts to applied forces to develop the ability to perform the task. Crucially, we require coupled learning to be facilitated by physically plausible learning rules, meaning that learning requires only local responses and no explicit information about the desired functionality. We show that such local learning rules can be derived for any physical network, whether in equilibrium or in steady state, with specific focus on two particular systems, namely disordered flow networks and elastic networks. By applying and adapting advances of statistical learning theory to the physical world, we demonstrate the plausibility of new classes of smart metamaterials capable of adapting to users’ needs in situ.Menachem SternDaniel HexnerJason W. RocksAndrea J. LiuAmerican Physical SocietyarticlePhysicsQC1-999ENPhysical Review X, Vol 11, Iss 2, p 021045 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Physics QC1-999
spellingShingle	Physics QC1-999 Menachem Stern Daniel Hexner Jason W. Rocks Andrea J. Liu Supervised Learning in Physical Networks: From Machine Learning to Learning Machines
description	Materials and machines are often designed with particular goals in mind, so that they exhibit desired responses to given forces or constraints. Here we explore an alternative approach, namely physical coupled learning. In this paradigm, the system is not initially designed to accomplish a task, but physically adapts to applied forces to develop the ability to perform the task. Crucially, we require coupled learning to be facilitated by physically plausible learning rules, meaning that learning requires only local responses and no explicit information about the desired functionality. We show that such local learning rules can be derived for any physical network, whether in equilibrium or in steady state, with specific focus on two particular systems, namely disordered flow networks and elastic networks. By applying and adapting advances of statistical learning theory to the physical world, we demonstrate the plausibility of new classes of smart metamaterials capable of adapting to users’ needs in situ.
format	article
author	Menachem Stern Daniel Hexner Jason W. Rocks Andrea J. Liu
author_facet	Menachem Stern Daniel Hexner Jason W. Rocks Andrea J. Liu
author_sort	Menachem Stern
title	Supervised Learning in Physical Networks: From Machine Learning to Learning Machines
title_short	Supervised Learning in Physical Networks: From Machine Learning to Learning Machines
title_full	Supervised Learning in Physical Networks: From Machine Learning to Learning Machines
title_fullStr	Supervised Learning in Physical Networks: From Machine Learning to Learning Machines
title_full_unstemmed	Supervised Learning in Physical Networks: From Machine Learning to Learning Machines
title_sort	supervised learning in physical networks: from machine learning to learning machines
publisher	American Physical Society
publishDate	2021
url	https://doaj.org/article/bfdef93505ef4ccea0370881623d513f
work_keys_str_mv	AT menachemstern supervisedlearninginphysicalnetworksfrommachinelearningtolearningmachines AT danielhexner supervisedlearninginphysicalnetworksfrommachinelearningtolearningmachines AT jasonwrocks supervisedlearninginphysicalnetworksfrommachinelearningtolearningmachines AT andreajliu supervisedlearninginphysicalnetworksfrommachinelearningtolearningmachines
_version_	1718385775030042624

Supervised Learning in Physical Networks: From Machine Learning to Learning Machines

Ejemplares similares