Keys to Accurate Feature Extraction Using Residual Spiking Neural Networks

Abstract

Spiking neural networks (SNNs) have become an interesting alternative to conventional artificial neural networks (ANN) thanks to their temporal processing capabilities and their low-SWaP (Size, Weight, and Power) and energy efficient implementations in neuromorphic hardware. However the challenges involved in training SNNs have limited their performance in terms of accuracy and thus their applications. Improving learning algorithms and neural architectures for a more accurate feature extraction is therefore one of the current priorities in SNN research. In this paper we present a study on the key components of modern spiking architectures. We empirically compare different techniques in image classification datasets taken from the best performing networks. We design a spiking version of the successful residual network (ResNet) architecture and test different components and training strategies on it. Our results provide a state of the art guide to SNN design, which allows to make informed choices when trying to build the optimal visual feature extractor. Finally, our network outperforms previous SNN architectures in and CIFAR-100 (74.5%) datasets and matches the state of the art in DVS-CIFAR10 (71.3%), with less parameters than the previous state of the art and without the need for ANN-SNN conversion. Code available at https://github. com/VicenteAlex/Spiking_ResNet

SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence

“…The increasing number of adoptions by the community is symbolic of the success of a framework. Since being open-sourced in December 2019, SpikingJelly has been widely used in many spiking deep learning studies, including adversarial attack (100, 101), ANN2SNN (95,(102)(103)(104)(105)(106), attention mechanisms (107,108), depth estimation from DVS data (69,109), development of innovative materials (110), emotion recognition (111), energy estimation (112), eventbased video reconstruction (113), fault diagnosis (114), hardware design (115)(116)(117), network structure improvements (60,61,(118)(119)(120)(121), spiking neuron improvements (56,(122)(123)(124)(125)(126)(127), training method improvements (128)(129)(130)(131)(132)(133)(134)(135)(136)(137)(138), medical diagnosis (139,140), network pruning …”