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

Davide L. Manna; Alex Vicente-Sola; Paul Kirkland; Trevor J. Bihl; Gaetano Di Caterina

doi:10.1007/978-3-031-34204-2_20

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

Davide L. Manna, Alex Vicente-Sola, Paul Kirkland, Trevor J. Bihl, Gaetano Di Caterina

Research output: Chapter in Book / Conference Paper › Chapter › peer-review

8 Citations (Scopus)

Abstract

The Neuromorphic (NM) field has seen significant growth in recent years, especially in the development of Machine Learning (ML) applications. Developing effective learning systems for such applications requires extensive experimentation and simulation, which can be facilitated by using software frameworks that provide researchers with a set of ready-to-use tools. The NM technological landscape has witnessed the emergence of several new frameworks in addition to the existing libraries in neuroscience fields. This work reviews nine frameworks for developing 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 enables users to incorporate a broader range of neuron models in SNNs trained with Spike-Timing-Dependent Plasticity (STDP). The extended code is made available to the public, providing a valuable resource for researchers in this field.

Original language	English
Title of host publication	Engineering Applications of Neural Networks: 24th International Conference, EAAAI/EANN 2023, León, Spain, June 14-17, 2023, Proceedings
Editors	Lazaros Iliadis, Ilias Maglogiannis, Serafin Alonso, Chrisina Jayne, Elias Pimenidis
Place of Publication	Switzerland
Publisher	Springer
Pages	227-238
Number of pages	12
ISBN (Electronic)	9783031342042
ISBN (Print)	9783031342035
DOIs	https://doi.org/10.1007/978-3-031-34204-2_20
Publication status	Published - 2023
Externally published	Yes
Event	International Conference on Engineering Applications of Neural Networks - León, Spain Duration: 14 Jun 2023 → 17 Jun 2023 Conference number: 24th

Publication series

Name	Communications in Computer and Information Science
Volume	1826
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	International Conference on Engineering Applications of Neural Networks
Abbreviated title	EANN
Country/Territory	Spain
City	León
Period	14/06/23 → 17/06/23

Keywords

frameworks
machine learning
neuromorphic
software
spiking neural networks
spiking neurons
unsupervised learning

Access to Document

10.1007/978-3-031-34204-2_20

Cite this

Manna, D. L., Vicente-Sola, A., Kirkland, P., Bihl, T. J., & Di Caterina, G. (2023). Frameworks for SNNs: a review of data science-oriented software and an expansion of SpykeTorch. In L. Iliadis, I. Maglogiannis, S. Alonso, C. Jayne, & E. Pimenidis (Eds.), Engineering Applications of Neural Networks: 24th International Conference, EAAAI/EANN 2023, León, Spain, June 14-17, 2023, Proceedings (pp. 227-238). (Communications in Computer and Information Science; Vol. 1826). Springer. https://doi.org/10.1007/978-3-031-34204-2_20

Manna, Davide L. ; Vicente-Sola, Alex ; Kirkland, Paul et al. / Frameworks for SNNs : a review of data science-oriented software and an expansion of SpykeTorch. Engineering Applications of Neural Networks: 24th International Conference, EAAAI/EANN 2023, León, Spain, June 14-17, 2023, Proceedings. editor / Lazaros Iliadis ; Ilias Maglogiannis ; Serafin Alonso ; Chrisina Jayne ; Elias Pimenidis. Switzerland : Springer, 2023. pp. 227-238 (Communications in Computer and Information Science).

@inbook{01ead668e5e5422588ae0c6f6bafbfa4,

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

abstract = "The Neuromorphic (NM) field has seen significant growth in recent years, especially in the development of Machine Learning (ML) applications. Developing effective learning systems for such applications requires extensive experimentation and simulation, which can be facilitated by using software frameworks that provide researchers with a set of ready-to-use tools. The NM technological landscape has witnessed the emergence of several new frameworks in addition to the existing libraries in neuroscience fields. This work reviews nine frameworks for developing 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 enables users to incorporate a broader range of neuron models in SNNs trained with Spike-Timing-Dependent Plasticity (STDP). The extended code is made available to the public, providing a valuable resource for researchers in this field.",

keywords = "frameworks, machine learning, neuromorphic, software, spiking neural networks, spiking neurons, unsupervised learning",

author = "Manna, {Davide L.} and Alex Vicente-Sola and Paul Kirkland and Bihl, {Trevor J.} and {Di Caterina}, Gaetano",

year = "2023",

doi = "10.1007/978-3-031-34204-2_20",

language = "English",

isbn = "9783031342035",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "227--238",

editor = "Lazaros Iliadis and Ilias Maglogiannis and Serafin Alonso and Chrisina Jayne and Elias Pimenidis",

booktitle = "Engineering Applications of Neural Networks: 24th International Conference, EAAAI/EANN 2023, Le{\'o}n, Spain, June 14-17, 2023, Proceedings",

note = "International Conference on Engineering Applications of Neural Networks, EANN ; Conference date: 14-06-2023 Through 17-06-2023",

}

Manna, DL, Vicente-Sola, A, Kirkland, P, Bihl, TJ & Di Caterina, G 2023, Frameworks for SNNs: a review of data science-oriented software and an expansion of SpykeTorch. in L Iliadis, I Maglogiannis, S Alonso, C Jayne & E Pimenidis (eds), Engineering Applications of Neural Networks: 24th International Conference, EAAAI/EANN 2023, León, Spain, June 14-17, 2023, Proceedings. Communications in Computer and Information Science, vol. 1826, Springer, Switzerland, pp. 227-238, International Conference on Engineering Applications of Neural Networks, León, Spain, 14/06/23. https://doi.org/10.1007/978-3-031-34204-2_20

Frameworks for SNNs: a review of data science-oriented software and an expansion of SpykeTorch. / Manna, Davide L.; Vicente-Sola, Alex; Kirkland, Paul et al.
Engineering Applications of Neural Networks: 24th International Conference, EAAAI/EANN 2023, León, Spain, June 14-17, 2023, Proceedings. ed. / Lazaros Iliadis; Ilias Maglogiannis; Serafin Alonso; Chrisina Jayne; Elias Pimenidis. Switzerland: Springer, 2023. p. 227-238 (Communications in Computer and Information Science; Vol. 1826).

Research output: Chapter in Book / Conference Paper › Chapter › peer-review

TY - CHAP

T1 - Frameworks for SNNs

T2 - International Conference on Engineering Applications of Neural Networks

AU - Manna, Davide L.

AU - Vicente-Sola, Alex

AU - Kirkland, Paul

AU - Bihl, Trevor J.

AU - Di Caterina, Gaetano

N1 - Conference code: 24th

PY - 2023

Y1 - 2023

N2 - The Neuromorphic (NM) field has seen significant growth in recent years, especially in the development of Machine Learning (ML) applications. Developing effective learning systems for such applications requires extensive experimentation and simulation, which can be facilitated by using software frameworks that provide researchers with a set of ready-to-use tools. The NM technological landscape has witnessed the emergence of several new frameworks in addition to the existing libraries in neuroscience fields. This work reviews nine frameworks for developing 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 enables users to incorporate a broader range of neuron models in SNNs trained with Spike-Timing-Dependent Plasticity (STDP). The extended code is made available to the public, providing a valuable resource for researchers in this field.

AB - The Neuromorphic (NM) field has seen significant growth in recent years, especially in the development of Machine Learning (ML) applications. Developing effective learning systems for such applications requires extensive experimentation and simulation, which can be facilitated by using software frameworks that provide researchers with a set of ready-to-use tools. The NM technological landscape has witnessed the emergence of several new frameworks in addition to the existing libraries in neuroscience fields. This work reviews nine frameworks for developing 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 enables users to incorporate a broader range of neuron models in SNNs trained with Spike-Timing-Dependent Plasticity (STDP). The extended code is made available to the public, providing a valuable resource for researchers in this field.

KW - frameworks

KW - machine learning

KW - neuromorphic

KW - software

KW - spiking neural networks

KW - spiking neurons

KW - unsupervised learning

UR - http://www.scopus.com/inward/record.url?scp=85163923094&partnerID=8YFLogxK

UR - https://go.openathens.net/redirector/westernsydney.edu.au?url=https://doi.org/10.1007/978-3-031-34204-2_20

U2 - 10.1007/978-3-031-34204-2_20

DO - 10.1007/978-3-031-34204-2_20

M3 - Chapter

AN - SCOPUS:85163923094

SN - 9783031342035

T3 - Communications in Computer and Information Science

SP - 227

EP - 238

BT - Engineering Applications of Neural Networks: 24th International Conference, EAAAI/EANN 2023, León, Spain, June 14-17, 2023, Proceedings

A2 - Iliadis, Lazaros

A2 - Maglogiannis, Ilias

A2 - Alonso, Serafin

A2 - Jayne, Chrisina

A2 - Pimenidis, Elias

PB - Springer

CY - Switzerland

Y2 - 14 June 2023 through 17 June 2023

ER -

Manna DL, Vicente-Sola A, Kirkland P, Bihl TJ, Di Caterina G. Frameworks for SNNs: a review of data science-oriented software and an expansion of SpykeTorch. In Iliadis L, Maglogiannis I, Alonso S, Jayne C, Pimenidis E, editors, Engineering Applications of Neural Networks: 24th International Conference, EAAAI/EANN 2023, León, Spain, June 14-17, 2023, Proceedings. Switzerland: Springer. 2023. p. 227-238. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-34204-2_20