Frameworks for SNNs: a Review of Data Science-oriented Software and an Expansion of SpykeTorch
This work provides a practical resource for researchers in neuromorphic computing by comparing frameworks and enhancing an existing tool, but it is incremental as it builds on prior software.
The paper reviews 9 data science-oriented frameworks for Spiking Neural Networks (SNNs), focusing on spiking neuron models and learning rules to guide research decisions, and extends the SpykeTorch framework to offer a broader choice of neuron models with publicly available code.
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.