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

Manna, Davide L. and Vicente-Sola, Alex and Kirkland, Paul and Bihl, Trevor J. and Di Caterina, Gaetano (2023) Frameworks for SNN : a review of data science-oriented software and an expansion of SpykeTorch. In: Engineering Applications and Advances of Artificial Intelligence, 2023-06-14 - 2023-06-17, University of León.

[thumbnail of Manna-etal-EAAAI-2023-Frameworks-for-SNNs-a-review-of-data]
Text. Filename: Manna_etal_EAAAI_2023_Frameworks_for_SNNs_a_review_of_data.pdf
Accepted Author Manuscript
License: Strathprints license 1.0

Download (950kB)| Preview


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.