Design-Space Exploration of SNN Models using Application-Specific Multi-Core Architectures

TL;DR

The paper addresses the challenge of understanding and efficiently implementing spike-timing-based spiking neural networks (SNNs) and the lack of interactive run-time analysis tools. It introduces RAVSim, a run-time multi-core architecture-based SNN simulator implemented in LabVIEW, enabling real-time interaction, visualization, and on-the-fly parameter tuning. The work outlines a project aimed at resource-efficient SNN designs for online learning and computer vision, exploring design space on CPU-based multi-core platforms and evaluating multiple neuron and synapse models. RAVSim is presented as an open-source solution with accompanying manuals and demos, and future directions include expanding neuron models, learning techniques, and real-time computer vision applications with event-based cameras, potentially accelerating design, prototyping, and parameter tuning in SNN research.

Abstract

With the motivation and the difficulties that currently exist in comprehending and utilizing the promising features of SNNs, we proposed a novel run-time multi-core architecture-based simulator called "RAVSim" (Runtime Analysis and Visualization Simulator), a cutting-edge SNN simulator, developed using LabVIEW and it is publicly available on their website as an official module. RAVSim is a runtime virtual simulation environment tool that enables the user to interact with the model, observe its behavior of output concentration, and modify the set of parametric values at any time while the simulation is in execution. Recently some popular tools have been presented, but we believe that none of the tools allow users to interact with the model simulation in run time.