Spyker: High-performance Library for Spiking Deep Neural Networks

TL;DR

Spyker is a high-performance C++/CUDA library for simulating large-scale spiking neural networks, enabling practical research and demonstrating the applicability of SNNs in modeling brain functions.

Contribution

The paper introduces Spyker, a novel, modular, high-performance library for large-scale SNN simulation, surpassing previous tools in speed and scalability.

Findings

Spyker achieves significantly faster runtimes than previous tools.

SNNs implemented with Spyker outperform prior implementations in large-scale simulations.

Comparison with electrophysiology data validates SNNs' potential to model brain activity.

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.