Asynchronous Bioplausible Neuron for SNN for Event Vision

TL;DR

This paper introduces the Asynchronous Bioplausible Neuron (ABN), a novel dynamic spike firing mechanism for SNNs that improves energy efficiency, neural homeostasis, and performance in event-based vision tasks.

Contribution

It presents a new neuron model that auto-adjusts to input variations, enhancing the stability and efficiency of spiking neural networks for visual processing.

Findings

ABN improves image classification accuracy.

ABN maintains neural homeostasis effectively.

ABN reduces energy consumption in SNNs.

Abstract

Spiking Neural Networks (SNNs) offer a biologically inspired approach to computer vision that can lead to more efficient processing of visual data with reduced energy consumption. However, maintaining homeostasis within these networks is challenging, as it requires continuous adjustment of neural responses to preserve equilibrium and optimal processing efficiency amidst diverse and often unpredictable input signals. In response to these challenges, we propose the Asynchronous Bioplausible Neuron (ABN), a dynamic spike firing mechanism to auto-adjust the variations in the input signal. Comprehensive evaluation across various datasets demonstrates ABN's enhanced performance in image classification and segmentation, maintenance of neural equilibrium, and energy efficiency.