Abstract
Spiking neural networks (SNNs) have been recently brought to light due to their promising capabilities. SNNs simulate the brain with higher biological plausibility compared to previous generations of neural networks. Learning with fewer samples and consuming less power are among the key features of these networks. However, the theoretical advantages of SNNs have not been seen in practice due to the slowness of simulation tools and the impracticality of the proposed network structures. In this work, we implement a high-performance library named Spyker using C++/CUDA from scratch that outperforms its predecessor. Several SNNs are implemented in this work with different learning rules (spike-timing-dependent plasticity and reinforcement learning) using Spyker that achieve significantly better runtimes, to prove the practicality of the library in the simulation of large-scale networks. To our knowledge, no such tools have been developed to simulate large-scale spiking neural networks with high performance using a modular structure. Furthermore, a comparison of the represented stimuli extracted from Spyker to recorded electrophysiology data is performed to demonstrate the applicability of SNNs in describing the underlying neural mechanisms of the brain functions. The aim of this library is to take a significant step toward uncovering the true potential of the brain computations using SNNs.
Abstract (translated)
Spiking neural networks (SNNs) 因为他们的潜力而最近被揭示。与前几代神经网络相比,SNNs 更能够模拟大脑。SNNs 使用更少样本和学习,消耗更少的能量,是这些网络的关键特征之一。然而,SNNs 的理论优势在实践中没有体现,因为模拟工具的速度太慢,以及所提出的网络结构不切实际。在本研究中,我们从头开始使用C++/CUDA编写名为Spyker 的高性能库,它比其前任表现得更好。在本研究中,我们使用Spyker 实现了多个SNNs,采用不同的学习规则( spike-timing-dependent plasticity 和 reinforcement learning),这些SNNs 实现了显著更好的运行时间,以证明库在大规模网络模拟中的实用性。据我们所知,目前还没有开发用于模拟大规模Spiking neural networks 并以高性能模块化实现的库。此外,我们进行了比较 Spyker 提取的代表刺激与记录电生理学数据的录制数据,以证明SNNs 在描述大脑功能基本神经网络机制方面的适用性。本库的目标是迈出一个重要的步骤,揭示使用SNNs 进行大脑计算的真正潜力。
URL
https://arxiv.org/abs/2301.13659
