Frameworks for SNNs: a review of data science-oriented software and an expansion of SpykeTorch

Davide Liberato Manna, Alex Vicente Sola, Paul Kirkland, Trevor Joseph Bihl, Gaetano Di Caterina

Research output: Contribution to conferencePosterpeer-review

80 Downloads (Pure)

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 belonged to neuroscience fields. This work reviews 9 frameworks for the development of Spiking Neural Networks (SNNs) that are specifically oriented towards data science applications. Furthermore, we present an extension to the SpykeTorch framework that gives users access to a much broader choice of spiking neurons to embed in SNNs and make the code publicly available.
Original languageEnglish
Number of pages8
Publication statusSubmitted - 13 Jun 2022
EventInternational Conference On Neuromorphic Systems 2022 - Knoxville, United States
Duration: 27 Jul 202229 Jul 2022

Conference

ConferenceInternational Conference On Neuromorphic Systems 2022
Abbreviated titleICONS 2022
Country/TerritoryUnited States
CityKnoxville
Period27/07/2229/07/22

Keywords

  • frameworks
  • spiking neural networks
  • spiking neurons
  • algorithms
  • neuromorphic

Fingerprint

Dive into the research topics of 'Frameworks for SNNs: a review of data science-oriented software and an expansion of SpykeTorch'. Together they form a unique fingerprint.

Cite this