Reservoir Computation with Networks of Differentiating Neuron Ring Oscillators

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yeung, Alexander, DelMastro, Peter, Karuvally, Arjun, Siegelmann, Hava, Rietman, Edward, Hazan, Hananel
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909710178844672
author Yeung, Alexander
DelMastro, Peter
Karuvally, Arjun
Siegelmann, Hava
Rietman, Edward
Hazan, Hananel
author_facet Yeung, Alexander
DelMastro, Peter
Karuvally, Arjun
Siegelmann, Hava
Rietman, Edward
Hazan, Hananel
contents Reservoir Computing is a machine learning approach that uses the rich repertoire of complex system dynamics for function approximation. Current approaches to reservoir computing use a network of coupled integrating neurons that require a steady current to maintain activity. Here, we introduce a small world graph of differentiating neurons that are active only when there are changes in input as an alternative to integrating neurons as a reservoir computing substrate. We find the coupling strength and network topology that enable these small world networks to function as an effective reservoir. We demonstrate the efficacy of these networks in the MNIST digit recognition task, achieving comparable performance of 90.65% to existing reservoir computing approaches. The findings suggest that differentiating neurons can be a potential alternative to integrating neurons and can provide a sustainable future alternative for power-hungry AI applications.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21377
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reservoir Computation with Networks of Differentiating Neuron Ring Oscillators
Yeung, Alexander
DelMastro, Peter
Karuvally, Arjun
Siegelmann, Hava
Rietman, Edward
Hazan, Hananel
Neural and Evolutionary Computing
Machine Learning
Reservoir Computing is a machine learning approach that uses the rich repertoire of complex system dynamics for function approximation. Current approaches to reservoir computing use a network of coupled integrating neurons that require a steady current to maintain activity. Here, we introduce a small world graph of differentiating neurons that are active only when there are changes in input as an alternative to integrating neurons as a reservoir computing substrate. We find the coupling strength and network topology that enable these small world networks to function as an effective reservoir. We demonstrate the efficacy of these networks in the MNIST digit recognition task, achieving comparable performance of 90.65% to existing reservoir computing approaches. The findings suggest that differentiating neurons can be a potential alternative to integrating neurons and can provide a sustainable future alternative for power-hungry AI applications.
title Reservoir Computation with Networks of Differentiating Neuron Ring Oscillators
topic Neural and Evolutionary Computing
Machine Learning
url https://arxiv.org/abs/2507.21377