Frameworks for SNNs: a Review of Data Science-oriented Software and an Expansion of SpykeTorch

TL;DR

This paper reviews nine software frameworks for Spiking Neural Networks tailored for data science, highlighting their features and introducing an extension to SpykeTorch that broadens neuron model options.

Contribution

It provides a comprehensive review of SNN frameworks and introduces an extended version of SpykeTorch with additional neuron models for research flexibility.

Findings

Nine frameworks analyzed for data science applications.

Extended SpykeTorch with more neuron models available.

Guidance on choosing frameworks based on neuron models.

Abstract

Developing effective learning systems for Machine Learning (ML) applications in the Neuromorphic (NM) field requires extensive experimentation and simulation. Software frameworks aid and ease this process by providing a set of ready-to-use tools that researchers can leverage. The recent interest in NM technology has seen the development of several new frameworks that do this, and that add up to the panorama of already existing libraries that belong to neuroscience fields. This work reviews 9 frameworks for the development of Spiking Neural Networks (SNNs) that are specifically oriented towards data science applications. We emphasize the availability of spiking neuron models and learning rules to more easily direct decisions on the most suitable frameworks to carry out different types of research. Furthermore, we present an extension to the SpykeTorch framework that gives users access to a much broader choice of neuron models to embed in SNNs and make the code publicly available.