Skip to main content

ORIGINAL RESEARCH article

Front. Neurosci.
Sec. Neuromorphic Engineering
Volume 18 - 2024 | doi: 10.3389/fnins.2024.1420119
This article is part of the Research Topic Deep Spiking Neural Networks: Models, Algorithms and Applications View all 6 articles

BayesianSpikeFusion: Accelerating Spiking Neural Network Inference via Bayesian Fusion of Early Prediction

Provisionally accepted
Takehiro Habara Takehiro Habara *Takashi Sato Takashi Sato Hiromitsu Awano Hiromitsu Awano
  • Kyoto University, Kyoto, Japan

The final, formatted version of the article will be published soon.

    Spiking neural networks (SNNs) have garnered significant attention due to their notable energy efficiency. However, conventional SNNs rely on spike firing frequency to encode information, necessitating a fixed sampling time and leaving room for further optimization. This study presents a novel approach to reduce sampling time and conserve energy by extracting early prediction results from the intermediate layer of the network and integrating them with the final layer's predictions in a Bayesian fashion. Experimental evaluations conducted on image classification tasks using MNIST, CIFAR-10, and CIFAR-100 datasets demonstrate the efficacy of our proposed method when applied to VGGNets and ResNets models. Results indicate a substantial energy reduction of 39.2%38.8% in VGGNets and 48.1%48.0% in ResNets, illustrating the potential for achieving significant efficiency gains in spiking neural networks.These findings contribute to the ongoing research in enhancing the performance of SNNs, facilitating their deployment in resource-constrained environments. Our code is available on GitHub. https://github.com/hanebarla/BayesianSpikeFusion

    Keywords: Spiking Neural network, Bayesian inference, neuromorphic computing, image classification, spiking network conversion

    Received: 19 Apr 2024; Accepted: 15 Jul 2024.

    Copyright: © 2024 Habara, Sato and Awano. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Takehiro Habara, Kyoto University, Kyoto, Japan

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.