Inferno: An Extensible Framework for Spiking Neural Networks

TL;DR

Inferno is a flexible, PyTorch-based software library that simplifies developing and deploying spiking neural networks across CPUs and GPUs, supporting advanced features like trainable delays and enabling novel research.

Contribution

The paper presents Inferno, a new extensible framework for SNNs that supports heterogeneous delays and a unified development approach, improving upon existing libraries.

Findings

Inferno supports trainable delays on CPUs and GPUs.

Inferno enables a 'write once, apply everywhere' development methodology.

Inferno facilitates implementation of advanced delay learning methods.

Abstract

This paper introduces Inferno, a software library built on top of PyTorch that is designed to meet distinctive challenges of using spiking neural networks (SNNs) for machine learning tasks. We describe the architecture of Inferno and key differentiators that make it uniquely well-suited to these tasks. We show how Inferno supports trainable heterogeneous delays on both CPUs and GPUs, and how Inferno enables a "write once, apply everywhere" development methodology for novel models and techniques. We compare Inferno's performance to BindsNET, a library aimed at machine learning with SNNs, and Brian2/Brian2CUDA which is popular in neuroscience. Among several examples, we show how the design decisions made by Inferno facilitate easily implementing the new methods of Nadafian and Ganjtabesh in delay learning with spike-timing dependent plasticity.