IBM/exact-mapping-ReLUnetwork-SNN: An Exact Mapping From ReLU Networks to Spiking Neural Networks

This repository contains code material for the publication: Stanojevic, A., Woźniak, S., Bellec, G., Cherubini, G., Pantazi, A., & Gerstner, W. (2022). An Exact Mapping From ReLU Networks to Spiking Neural Networks. arXiv preprint arXiv:2212.12522. https://arxiv.org/abs/2212.12522 Deep spiking neural networks (SNNs) offer the promise of low-power artificial intelligence. However, training deep SNNs from scratch or converting deep artificial neural networks to SNNs without loss of performance has been a challenge. An exact mapping enables to convert a pretrained high-performance network with Rectified Linear Units (ReLUs) to an energy-efficient SNN with zero percent drop in accuracy. The exact mapping is coded in Python and Tensorflow