23rd EANN / EAAAI 2022, 17 - 20 June 2022, Greece

SNNs Model Analyzing and Visualizing Experimentation using RAVSim

Sanaullah, Shamini Koravuna, Ulrich Rückert, Thorsten Jungeblut


  Spiking Neural Networks (SNNs) reduce the computational complexity compared to traditional artificial neural networks (ANN) by introducing the spike coding method and the nonlinear activated neuron model and transmitting only the binary spike events. However, these complex model simulations and behavioral analysis are a standard approach of parametric values verification prior to their physical implementation on the hardware. 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. The run-time interaction with the simulation creates a full understanding of these complex SNNs model mechanisms which is a quite challenging process, especially for early-stage researchers and students. In this paper, we present the first version of our novel spiking neural network user-friendly software tool named RAVSim (Real-time Analysis and Visualization Simulator), which provides a runtime environment to analyze and simulate the SNNs model. It is an interactive and intuitive tool designed to help in knowing considerable parameters involved in the working of the neurons, their dependency on each other, determining the essential parametric values, and the communication between the neurons for replicating the way the human brain works. Moreover, the proposed SNNs model analysis and simulation algorithm used in RAVSim takes significantly less time in order to estimate and visualize the behavior of the parametric values during a runtime environment.  

*** Title, author list and abstract as seen in the Camera-Ready version of the paper that was provided to Conference Committee. Small changes that may have occurred during processing by Springer may not appear in this window.