Motif-topology improved Spiking Neural Network for the Cocktail Party Effect and McGurk Effect

TL;DR

This paper introduces a motif-topology enhanced spiking neural network (M-SNN) that improves multi-sensory integration and effectively simulates cognitive phenomena like the cocktail party and McGurk effects with higher accuracy and lower computational cost.

Contribution

The study proposes a novel M-SNN architecture using network motifs derived from datasets, enhancing multi-sensory integration and cognitive phenomenon simulation over existing models.

Findings

M-SNN outperforms pure feedforward networks in single-sensory classification accuracy.

M-SNN surpasses state-of-the-art SNN with BRP in multi-sensory integration tasks.

M-SNN better simulates cocktail party and McGurk effects with lower computational cost.

Abstract

Network architectures and learning principles are playing key in forming complex functions in artificial neural networks (ANNs) and spiking neural networks (SNNs). SNNs are considered the new-generation artificial networks by incorporating more biological features than ANNs, including dynamic spiking neurons, functionally specified architectures, and efficient learning paradigms. Network architectures are also considered embodying the function of the network. Here, we propose a Motif-topology improved SNN (M-SNN) for the efficient multi-sensory integration and cognitive phenomenon simulations. The cognitive phenomenon simulation we simulated includes the cocktail party effect and McGurk effect, which are discussed by many researchers. Our M-SNN constituted by the meta operator called network motifs. The source of 3-node network motifs topology from artificial one pre-learned from the spatial or temporal dataset. In the single-sensory classification task, the results showed the accuracy of M-SNN using network motif topologies was higher than the pure feedforward network topology without using them. In the multi-sensory integration task, the performance of M-SNN using artificial network motif was better than the state-of-the-art SNN using BRP (biologically-plausible reward propagation). Furthermore, the M-SNN could better simulate the cocktail party effect and McGurk effect with lower computational cost. We think the artificial network motifs could be considered as some prior knowledge that would contribute to the multi-sensory integration of SNNs and provide more benefits for simulating the cognitive phenomenon.