Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff

by   Dengyu Wu, et al.
University of Liverpool

Spiking neural networks (SNNs), a variant of artificial neural networks (ANNs) with the benefit of energy efficiency, have achieved the accuracy close to its ANN counterparts, on benchmark datasets such as CIFAR10/100 and ImageNet. However, comparing with frame-based input (e.g., images), event-based inputs from e.g., Dynamic Vision Sensor (DVS) can make a better use of SNNs thanks to the SNNs' asynchronous working mechanism. In this paper, we strengthen the marriage between SNNs and event-based inputs with a proposal to consider anytime optimal inference SNNs, or AOI-SNNs, which can terminate anytime during the inference to achieve optimal inference result. Two novel optimisation techniques are presented to achieve AOI-SNNs: a regularisation and a cutoff. The regularisation enables the training and construction of SNNs with optimised performance, and the cutoff technique optimises the inference of SNNs on event-driven inputs. We conduct an extensive set of experiments on multiple benchmark event-based datasets, including CIFAR10-DVS, N-Caltech101 and DVS128 Gesture. The experimental results demonstrate that our techniques are superior to the state-of-the-art with respect to the accuracy and latency.


page 1

page 2


Event-based Video Reconstruction via Potential-assisted Spiking Neural Network

Neuromorphic vision sensor is a new bio-inspired imaging paradigm that r...

BiSNN: Training Spiking Neural Networks with Binary Weights via Bayesian Learning

Artificial Neural Network (ANN)-based inference on battery-powered devic...

Robustness of classification ability of spiking neural networks

It is well-known that the robustness of artificial neural networks (ANNs...

Attention Spiking Neural Networks

Benefiting from the event-driven and sparse spiking characteristics of t...

Spiking-Fer: Spiking Neural Network for Facial Expression Recognition With Event Cameras

Facial Expression Recognition (FER) is an active research domain that ha...

The Spike Gating Flow: A Hierarchical Structure Based Spiking Neural Network for Online Gesture Recognition

Action recognition is an exciting research avenue for artificial intelli...

Rethinking Pretraining as a Bridge from ANNs to SNNs

Spiking neural networks (SNNs) are known as a typical kind of brain-insp...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset