Keys to Accurate Feature Extraction Using Residual Spiking Neural Networks

11/10/2021
by   Alex Vicente-Sola, et al.
7

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 CIFAR-10 (94.1 art in DVS-CIFAR10 (71.3 art and without the need for ANN-SNN conversion. Code available at https://github.com/VicenteAlex/Spiking_ResNet.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/27/2020

Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction

Spiking neural networks (SNNs) can be used in low-power and embedded sys...
research
12/23/2019

Intelligent Wireless Sensor Nodes for Human Footstep Sound Classification for Security Application

Sensor nodes present in a wireless sensor network (WSN) for security sur...
research
06/21/2023

Efficient Deep Spiking Multi-Layer Perceptrons with Multiplication-Free Inference

Advancements in adapting deep convolution architectures for Spiking Neur...
research
05/18/2023

SPENSER: Towards a NeuroEvolutionary Approach for Convolutional Spiking Neural Networks

Spiking Neural Networks (SNNs) have attracted recent interest due to the...
research
10/27/2020

Spiking Neural Networks – Part I: Detecting Spatial Patterns

Spiking Neural Networks (SNNs) are biologically inspired machine learnin...
research
02/07/2018

Going Deeper in Spiking Neural Networks: VGG and Residual Architectures

Over the past few years, Spiking Neural Networks (SNNs) have become popu...
research
11/14/2022

Wearable-based Human Activity Recognition with Spatio-Temporal Spiking Neural Networks

We study the Human Activity Recognition (HAR) task, which predicts user ...

Please sign up or login with your details

Forgot password? Click here to reset