CogniSNN: An Exploration to Random Graph Architecture based Spiking Neural Networks with Enhanced Depth-Scalability and Path-Plasticity

TL;DR

CogniSNN introduces a novel random graph architecture for spiking neural networks, enhancing depth scalability and path plasticity, and demonstrates improved performance and adaptability on neuromorphic datasets.

Contribution

This paper proposes a new RGA-based SNN model with a modified ResNode and path reusability algorithm, advancing biological plausibility and task adaptability in SNNs.

Findings

CogniSNN achieves comparable or superior performance to state-of-the-art SNNs.

The modified ResNode mitigates network degradation in deep pathways.

Path reusability enables effective learning of new tasks with previous features.

Abstract

Currently, most spiking neural networks (SNNs) still mimic the chain-like hierarchical architecture in traditional artificial neural networks (ANNs). This method significantly differs from random connections between neurons found in biological brains, limiting the ability to model the evolving mechanisms of neural pathways in biological neural systems, particularly in terms of dynamic depth-scalability and adaptive path-plasticity. This paper develops a new modeling paradigm for SNNs with random graph architecture (RGA), termed Cognition-aware SNN (CogniSNN). Furthermore, we model the depth-scalability and path-plasticity in CogniSNN by introducing a modified spiking residual neural node (ResNode) to counteract network degradation in deeper graph pathways, as well as a critical path-based algorithm that enables CogniSNN to perform path reusability on new tasks leveraging the features of the data and the RGA learned in old tasks. Experiments show that the performance of CogniSNN with redesigned ResNode is comparable, even superior, to current state-of-the-art SNNs on neuromorphic datasets. The critical path-based approach effectively achieves path reuse capability while maintaining expected performance in learning new tasks that are similar to or distinct from the old ones. This study showcases the potential of RGA-based SNNs and paves a new path for modeling the fusion of computational neuroscience and deep intelligent agents. The code is available at github.com/Yongsheng124/CogniSNN.