Publications

Detailed Information

Resting-potential-adjustable soft-reset integrate-and-fire neuron model for highly reliable and energy-efficient hardware-based spiking neural networks

DC Field Value Language
dc.contributor.authorPark, Kyungchul-
dc.contributor.authorKim, Sungjoon-
dc.contributor.authorOh, Min-Hye-
dc.contributor.authorChoi, Woo Young-
dc.date.accessioned2024-05-14T01:25:17Z-
dc.date.available2024-05-14T01:25:17Z-
dc.date.created2024-05-14-
dc.date.issued2024-
dc.identifier.citationNeurocomputing, Vol.590, p. 127762-
dc.identifier.issn0925-2312-
dc.identifier.urihttps://hdl.handle.net/10371/201629-
dc.description.abstractIn this study, the resting-potential-adjustable soft-reset (RSR) integrate-and-fire neuron model is proposed for higher reliability of hardware-based spiking neural networks (SNNs). Recently, researchers have attempted to implement neuronal models using hardware. However, previously proposed hard-reset (HR) and soft-reset (SR) neuron models are not suitable for hardware implementation for the following reasons. First, it is difficult to compensate for the neuron-threshold variation, which generally occurs in the fabrication processes. Second, they require a negative voltage supply that consumes substantial energy to implement the negative membrane potential (NMP). Third, for the HR and SR neuron models, maintaining the residual membrane potential (RMP) is challenging. The proposed RSR neuron model solves these challenges without any additional systems and algorithms and provides the following advantages: easy compensation for the neuron-threshold variation, significant energy reduction without using a negative voltage supply for the NMP, and precise preservation of the RMP. We discuss the behavior of the RSR neuron model and evaluate performance by comparing the inference results. Even with the neuron-threshold variation within the six-sigma range, the RSR neuron model restores the inference accuracy to the values of artificial neural networks (ANNs) for various datasets (CIFAR-10: 92.74%, SVHN: 95.00%, MNIST: 98.30%). In the case of the CIFAR-10, the RSR neuron model consumes 32.80% lower energy than the SR neuron model.-
dc.language영어-
dc.publisherElsevier BV-
dc.titleResting-potential-adjustable soft-reset integrate-and-fire neuron model for highly reliable and energy-efficient hardware-based spiking neural networks-
dc.typeArticle-
dc.identifier.doi10.1016/j.neucom.2024.127762-
dc.citation.journaltitleNeurocomputing-
dc.identifier.scopusid2-s2.0-85192086127-
dc.citation.startpage127762-
dc.citation.volume590-
dc.description.isOpenAccessN-
dc.contributor.affiliatedAuthorChoi, Woo Young-
dc.type.docTypeArticle-
dc.description.journalClass1-
dc.subject.keywordAuthorNegative membrane potential-
dc.subject.keywordAuthorNeuron model-
dc.subject.keywordAuthorResidual membrane potential-
dc.subject.keywordAuthorSpiking neural network-
dc.subject.keywordAuthorThreshold variation compensation-
Appears in Collections:
Files in This Item:
There are no files associated with this item.

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share