evt_MNIST: A spike based version of traditional MNIST

TL;DR

This paper introduces evt_MNIST, a spike-based adaptation of the traditional MNIST dataset using Poisson distributions to generate irregular spike streams, facilitating evaluation of spiking neural networks.

Contribution

The paper presents a novel spike-based MNIST dataset using Poisson processes, tailored for evaluating spiking neural network algorithms.

Findings

Poisson distribution effectively models spike irregularity.

evt_MNIST enables neural network evaluation with spike-based data.

The dataset captures biological spike timing characteristics.

Abstract

Benchmarks and datasets have important role in evaluation of machine learning algorithms and neural network implementations. Traditional dataset for images such as MNIST is applied to evaluate efficiency of different training algorithms in neural networks. This demand is different in Spiking Neural Networks (SNN) as they require spiking inputs. It is widely believed, in the biological cortex the timing of spikes is irregular. Poisson distributions provide adequate descriptions of the irregularity in generating appropriate spikes. Here, we introduce a spike-based version of MNSIT (handwritten digits dataset),using Poisson distribution and show the Poissonian property of the generated streams. We introduce a new version of evt_MNIST which can be used for neural network evaluation.