arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.04876cs.NEcs.AIcs.LG
收藏

脉冲神经网络的内在结构研究

On the Intrinsic Structures of Spiking Neural Networks

Nanjing University(南京大学);Nanjing Normal University(南京师范大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

Shao-Qun Zhang, Jia-Yi Chen, Jin-Hui Wu, Gao Zhang, Huan Xiong, Bin Gu, Zhi-Hua Zhou

AI总结:

本文研究脉冲神经网络的内在结构,揭示积分操作与发放-重置机制的关键作用,并提出自连接架构和随机脉冲神经元两种方法增强其适应性,从而提升SNN性能与适用性。

摘要:

近年来,由于脉冲神经网络(SNN)在处理时间依赖和事件驱动数据方面的显著潜力,对其研究兴趣激增。SNN的性能不仅取决于选择合适的架构和微调连接权重(类似于传统人工神经网络),还取决于脉冲计算中内在结构的细致配置。然而,缺乏全面研究内在结构影响的工作。因此,开发者通常难以在不同数据集或任务中应用标准化的SNN配置。本研究深入探讨了SNN的内在结构。首先,我们揭示了内在结构的两个关键组成部分:积分操作和发放-重置机制,通过阐明它们对SNN表达能力的影响。此外,我们得出两个关键结论:膜时间超参数与积分操作的特征值密切相关,决定了脉冲动力学的功能拓扑;发放-重置机制的各种超参数控制着SNN的整体发放能力,调节输入数据的注入比例或采样密度。这些发现阐明了为什么SNN的有效性高度依赖于内在结构的配置,并导致一个建议:增强这些结构的适应性有助于提高SNN的整体性能和适用性。受此认识启发,我们提出了两种可行的方法来增强SNN学习。这些方法分别利用自连接架构和随机脉冲神经元来增强积分操作和发放-重置机制的适应性。我们从理论和实践的角度验证了所提出方法的有效性。

英文摘要:

Recent years have emerged a surge of interest in SNNs owing to their remarkable potential to handle time-dependent and event-driven data. The performance of SNNs hinges not only on selecting an apposite architecture and fine-tuning connection weights, similar to conventional ANNs, but also on the meticulous configuration of intrinsic structures within spiking computations. However, there has been a dearth of comprehensive studies examining the impact of intrinsic structures. Consequently, developers often find it challenging to apply a standardized configuration of SNNs across diverse datasets or tasks. This work delves deep into the intrinsic structures of SNNs. Initially, we unveil two pivotal components of intrinsic structures: the integration operation and firing-reset mechanism, by elucidating their influence on the expressivity of SNNs. Furthermore, we draw two key conclusions: the membrane time hyper-parameter is intimately linked to the eigenvalues of the integration operation, dictating the functional topology of spiking dynamics, and various hyper-parameters of the firing-reset mechanism govern the overall firing capacity of an SNN, mitigating the injection ratio or sampling density of input data. These findings elucidate why the efficacy of SNNs hinges heavily on the configuration of intrinsic structures and lead to a recommendation that enhancing the adaptability of these structures contributes to improving the overall performance and applicability of SNNs. Inspired by this recognition, we propose two feasible approaches to enhance SNN learning. These involve leveraging self-connection architectures and employing stochastic spiking neurons to augment the adaptability of the integration operation and firing-reset mechanism, respectively. We verify the effectiveness of the proposed methods from perspectives of theory and practice.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑