A Versatile Hub Model For Efficient Information Propagation And Feature Selection

TL;DR

This paper introduces a mathematical hub model that enhances information propagation and feature selection in neural networks, demonstrating improved performance and mechanistic insights into hub structures in biological and artificial systems.

Contribution

A versatile mathematical model of hub structures applicable to neuroscience and RNNs, with empirical validation showing performance improvements.

Findings

Enhanced model performance with hub structures

Facilitated efficient information processing

Improved feature extraction capabilities

Abstract

Hub structure, characterized by a few highly interconnected nodes surrounded by a larger number of nodes with fewer connections, is a prominent topological feature of biological brains, contributing to efficient information transfer and cognitive processing across various species. In this paper, a mathematical model of hub structure is presented. The proposed method is versatile and can be broadly applied to both computational neuroscience and Recurrent Neural Networks (RNNs) research. We employ the Echo State Network (ESN) as a means to investigate the mechanistic underpinnings of hub structures. Our findings demonstrate a substantial enhancement in performance upon incorporating the hub structure. Through comprehensive mechanistic analyses, we show that the hub structure improves model performance by facilitating efficient information processing and better feature extractions.