# SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron

## TL;DR

SpykeTorch is a high-speed, open-source simulation framework for convolutional spiking neural networks that efficiently models at most one spike per neuron using PyTorch, enabling scalable AI applications.

## Contribution

It introduces a flexible, tensor-based simulation framework that supports efficient large-scale SNNs with single-spike neurons and multiple learning rules, optimized for various hardware platforms.

## Key findings

- Supports large-scale SNN simulation with high speed
- Flexible implementation of learning rules like STDP and R-STDP
- Optimized for CPU, GPU, and multi-GPU platforms

## Abstract

Application of deep convolutional spiking neural networks (SNNs) to artificial intelligence (AI) tasks has recently gained a lot of interest since SNNs are hardware-friendly and energy-efficient. Unlike the non-spiking counterparts, most of the existing SNN simulation frameworks are not practically efficient enough for large-scale AI tasks. In this paper, we introduce SpykeTorch, an open-source high-speed simulation framework based on PyTorch. This framework simulates convolutional SNNs with at most one spike per neuron and the rank-order encoding scheme. In terms of learning rules, both spike-timing-dependent plasticity (STDP) and reward-modulated STDP (R-STDP) are implemented, but other rules could be implemented easily. Apart from the aforementioned properties, SpykeTorch is highly generic and capable of reproducing the results of various studies. Computations in the proposed framework are tensor-based and totally done by PyTorch functions, which in turn brings the ability of just-in-time optimization for running on CPUs, GPUs, or Multi-GPU platforms.