Convolutional Spiking Neural Network for Image Classification

TL;DR

This paper introduces a convolutional spiking neural network architecture for image classification, utilizing fixed convolutional weights derived from representative images, and demonstrates its effectiveness on the NEOVISION2 benchmark.

Contribution

It presents a novel method for fixed convolutional weights in SNNs, aligning with biological principles, and applies it to image classification tasks.

Findings

Effective classification on NEOVISION2 benchmark

Fixed convolutional weights derived from representative images

Alignment with biological synaptic plasticity principles

Abstract

We consider an implementation of convolutional architecture in a spiking neural network (SNN) used to classify images. As in the traditional neural network, the convolutional layers form informational "features" used as predictors in the SNN-based classifier with CoLaNET architecture. Since weight sharing contradicts the synaptic plasticity locality principle, the convolutional weights are fixed in our approach. We describe a methodology for their determination from a representative set of images from the same domain as the classified ones. We illustrate and test our approach on a classification task from the NEOVISION2 benchmark.