Random Graph-Based Neuromorphic Learning with a Layer-Weaken Structure

TL;DR

This paper introduces a novel neuromorphic learning model called RGNN that uses random graph theory and Fourier Random Features to optimize neural network structures with reduced manual effort and computational cost, achieving improved classification performance.

Contribution

The paper proposes a new random graph-based neural network architecture that simplifies structure design and enhances supervised learning performance without fixed deep architectures.

Findings

Achieved significant performance improvements on three benchmark tasks.

Reduced manual intervention and computational cost in neural network design.

Effectively avoided interpretability issues impacting structure engineering.

Abstract

Unified understanding of neuro networks (NNs) gets the users into great trouble because they have been puzzled by what kind of rules should be obeyed to optimize the internal structure of NNs. Considering the potential capability of random graphs to alter how computation is performed, we demonstrate that they can serve as architecture generators to optimize the internal structure of NNs. To transform the random graph theory into an NN model with practical meaning and based on clarifying the input-output relationship of each neuron, we complete data feature mapping by calculating Fourier Random Features (FRFs). Under the usage of this low-operation cost approach, neurons are assigned to several groups of which connection relationships can be regarded as uniform representations of random graphs they belong to, and random arrangement fuses those neurons to establish the pattern matrix, markedly reducing manual participation and computational cost without the fixed and deep architecture. Leveraging this single neuromorphic learning model termed random graph-based neuro network (RGNN) we develop a joint classification mechanism involving information interaction between multiple RGNNs and realize significant performance improvements in supervised learning for three benchmark tasks, whereby they effectively avoid the adverse impact of the interpretability of NNs on the structure design and engineering practice.