Spiking neural networks: Towards bio-inspired multimodal perception in robotics

TL;DR

This paper explores enhancing the biological plausibility of spiking neural networks to improve bio-inspired multimodal perception in robotics, aiming for more human-like interaction capabilities.

Contribution

It proposes a brain-inspired approach combining audio-visual processing in SNNs to advance bio-plausible perception in robotics.

Findings

Enhanced bio-plausibility of SNNs demonstrated

Improved multimodal perception in robotic applications

Potential for more natural human-robot interactions

Abstract

Spiking neural networks (SNNs) have captured apparent interest over the recent years, stemming from neuroscience and reaching the field of artificial intelligence. However, due to their nature SNNs remain far behind in achieving the exceptional performance of deep neural networks (DNNs). As a result, many scholars are exploring ways to enhance SNNs by using learning techniques from DNNs. While this approach has been proven to achieve considerable improvements in SNN performance, we propose another perspective: enhancing the biological plausibility of the models to leverage the advantages of SNNs fully. Our approach aims to propose a brain-like combination of audio-visual signal processing for recognition tasks, intended to succeed in more bio-plausible human-robot interaction applications.