CHNNet: An Artificial Neural Network With Connected Hidden Neurons
This work addresses a structural gap in neural network design for researchers, but it is incremental as it builds on existing architectures with a specific modification.
The authors tackled the limitation of conventional neural networks lacking intra-layer connections by introducing CHNNet, which includes connections among hidden neurons, and demonstrated that it achieves faster convergence than standard feedforward networks.
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.