Salvato in:
Dettagli Bibliografici
Autori principali: Love, Jake, Mulkers, Jeroen, Msiska, Robin, Bourianoff, George, Leliaert, Jonathan, Everschor-Sitte, Karin
Natura: Preprint
Pubblicazione: 2021
Soggetti:
Accesso online:https://arxiv.org/abs/2108.01512
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911039915819008
author Love, Jake
Mulkers, Jeroen
Msiska, Robin
Bourianoff, George
Leliaert, Jonathan
Everschor-Sitte, Karin
author_facet Love, Jake
Mulkers, Jeroen
Msiska, Robin
Bourianoff, George
Leliaert, Jonathan
Everschor-Sitte, Karin
contents Physical reservoir computing is a computational framework that implements spatiotemporal information processing directly within physical systems. By exciting nonlinear dynamical systems and creating linear models from their state, we can create highly energy-efficient devices capable of solving machine learning tasks without building a modular system consisting of millions of neurons interconnected by synapses. To act as an effective reservoir, the chosen dynamical system must have two desirable properties: nonlinearity and memory. We present task agnostic spatial measures to locally measure both of these properties and exemplify them for a specific physical reservoir based upon magnetic skyrmion textures. In contrast to typical reservoir computing metrics, these metrics can be resolved spatially and in parallel from a single input signal, allowing for efficient parameter search to design efficient and high-performance reservoirs. Additionally, we show the natural trade-off between memory capacity and nonlinearity in our reservoir's behaviour, both locally and globally. Finally, by balancing the memory and nonlinearity in a reservoir, we can improve its performance for specific tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2108_01512
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Spatial Analysis of Physical Reservoir Computers
Love, Jake
Mulkers, Jeroen
Msiska, Robin
Bourianoff, George
Leliaert, Jonathan
Everschor-Sitte, Karin
Machine Learning
Disordered Systems and Neural Networks
Other Condensed Matter
Strongly Correlated Electrons
Neural and Evolutionary Computing
Physical reservoir computing is a computational framework that implements spatiotemporal information processing directly within physical systems. By exciting nonlinear dynamical systems and creating linear models from their state, we can create highly energy-efficient devices capable of solving machine learning tasks without building a modular system consisting of millions of neurons interconnected by synapses. To act as an effective reservoir, the chosen dynamical system must have two desirable properties: nonlinearity and memory. We present task agnostic spatial measures to locally measure both of these properties and exemplify them for a specific physical reservoir based upon magnetic skyrmion textures. In contrast to typical reservoir computing metrics, these metrics can be resolved spatially and in parallel from a single input signal, allowing for efficient parameter search to design efficient and high-performance reservoirs. Additionally, we show the natural trade-off between memory capacity and nonlinearity in our reservoir's behaviour, both locally and globally. Finally, by balancing the memory and nonlinearity in a reservoir, we can improve its performance for specific tasks.
title Spatial Analysis of Physical Reservoir Computers
topic Machine Learning
Disordered Systems and Neural Networks
Other Condensed Matter
Strongly Correlated Electrons
Neural and Evolutionary Computing
url https://arxiv.org/abs/2108.01512