CHNNet: An Artificial Neural Network With Connected Hidden Neurons

TL;DR

This paper introduces CHNNet, a neural network with intra-layer hidden neuron connections, aiming to enhance information integration and convergence speed over traditional hierarchical architectures.

Contribution

The paper proposes a novel neural network architecture with intra-layer connections among hidden neurons, enabling better intra-layer information flow and faster convergence.

Findings

The intra-layer connected network converges faster than traditional models.

Experimental results validate the theoretical advantages of intra-layer connections.

The model improves intra-layer information integration.

Abstract

In contrast to biological neural circuits, conventional artificial neural networks are commonly organized as strictly hierarchical architectures that exclude direct connections among neurons within the same layer. Consequently, information flow is primarily confined to feedforward and feedback pathways across layers, which limits lateral interactions and constrains the potential for intra-layer information integration. We introduce an artificial neural network featuring intra-layer connections among hidden neurons to overcome this limitation. Owing to the proposed method for facilitating intra-layer connections, the model is theoretically anticipated to achieve faster convergence compared to conventional feedforward neural networks. The experimental findings provide further validation of the theoretical analysis.