Optimizing Spatio-Temporal Information Processing in Spiking Neural Networks via Unconstrained Leaky Integrate-and-Fire Neurons and Hybrid Coding

TL;DR

This paper introduces an unconstrained neuronal model and a hybrid encoding scheme to enhance the spatio-temporal processing capabilities of Spiking Neural Networks, leading to improved performance in object detection and recognition tasks.

Contribution

The paper proposes a novel ULIF neuronal model and hybrid encoding scheme to better exploit spatio-temporal information in SNNs, addressing internal and external limitations.

Findings

Improved object detection accuracy with the proposed methods.

Enhanced ability of SNNs to process complex temporal information.

Code availability facilitates reproducibility and further research.

Abstract

Spiking Neural Networks (SNN) exhibit higher energy efficiency compared to Artificial Neural Networks (ANN) due to their unique spike-driven mechanism. Additionally, SNN possess a crucial characteristic, namely the ability to process spatio-temporal information. However, this ability is constrained by both internal and external factors in practical applications, thereby affecting the performance of SNN. Firstly, the internal issue of SNN lies in the inherent limitations of their network structure and neuronal model, which result in the network adopting a unified processing approach for information of different temporal dimensions when processing input data containing complex temporal information. Secondly, the external issue of SNN stems from the direct encoding method commonly adopted by directly trained SNN, which uses the same feature map for input at each time step, failing to fully exploit the spatio-temporal characteristics of SNN. To address these issues, this paper proposes an Unconstrained Leaky Integrate-and-Fire (ULIF) neuronal model that allows for learning different membrane potential parameters at different time steps, thereby enhancing SNN' ability to process information of different temporal dimensions. Additionally, this paper presents a hybrid encoding scheme aimed at solving the problem of direct encoding lacking temporal dimension information. Experimental results demonstrate that the proposed methods effectively improve the overall performance of SNN in object detection and object recognition tasks. related code is available at https://github.com/hhx0320/ASNN.