Audio Classification with Skyrmion Reservoirs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Msiska, Robin, Love, Jake, Mulkers, Jeroen, Leliaert, Jonathan, Everschor-Sitte, Karin
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913924907008000
author Msiska, Robin
Love, Jake
Mulkers, Jeroen
Leliaert, Jonathan
Everschor-Sitte, Karin
author_facet Msiska, Robin
Love, Jake
Mulkers, Jeroen
Leliaert, Jonathan
Everschor-Sitte, Karin
contents Physical reservoir computing is a computational paradigm that enables spatio-temporal pattern recognition to be performed directly in matter. The use of physical matter leads the way towards energy-efficient devices capable of solving machine learning problems without having to build a system of millions of interconnected neurons. We propose a high performance "skyrmion mixture reservoir" that implements the reservoir computing model with multi-dimensional inputs. We show that our implementation solves spoken digit classification tasks at the nanosecond timescale, with an overall model accuracy of 97.4% and a less that 1% word error rate; the best performance ever reported for in-materio reservoir computers. Due to the quality of the results and the low power properties of magnetic texture reservoirs, we argue that skyrmion fabrics are a compelling candidate for reservoir computing.
format Preprint
id arxiv_https___arxiv_org_abs_2209_13946
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Audio Classification with Skyrmion Reservoirs
Msiska, Robin
Love, Jake
Mulkers, Jeroen
Leliaert, Jonathan
Everschor-Sitte, Karin
Mesoscale and Nanoscale Physics
Physical reservoir computing is a computational paradigm that enables spatio-temporal pattern recognition to be performed directly in matter. The use of physical matter leads the way towards energy-efficient devices capable of solving machine learning problems without having to build a system of millions of interconnected neurons. We propose a high performance "skyrmion mixture reservoir" that implements the reservoir computing model with multi-dimensional inputs. We show that our implementation solves spoken digit classification tasks at the nanosecond timescale, with an overall model accuracy of 97.4% and a less that 1% word error rate; the best performance ever reported for in-materio reservoir computers. Due to the quality of the results and the low power properties of magnetic texture reservoirs, we argue that skyrmion fabrics are a compelling candidate for reservoir computing.
title Audio Classification with Skyrmion Reservoirs
topic Mesoscale and Nanoscale Physics
url https://arxiv.org/abs/2209.13946