A Multi-In and Multi-Out Dendritic Neuron Model and its Optimization

TL;DR

This paper introduces a multi-in and multi-out dendritic neuron model (MODN) that enhances the original DNM by enabling multi-output processing and adaptive dendrite selection, improving performance on classification tasks.

Contribution

The paper proposes a novel MODN framework with a learnable filtering matrix and telodendron layer, extending DNM capabilities to multi-output tasks and providing a unified, adaptable model.

Findings

MODN outperforms existing models in accuracy

MODN demonstrates faster convergence

MODN shows strong generalization across datasets

Abstract

Artificial neural networks (ANNs), inspired by the interconnection of real neurons, have achieved unprecedented success in various fields such as computer vision and natural language processing. Recently, a novel mathematical ANN model, known as the dendritic neuron model (DNM), has been proposed to address nonlinear problems by more accurately reflecting the structure of real neurons. However, the single-output design limits its capability to handle multi-output tasks, significantly lowering its applications. In this paper, we propose a novel multi-in and multi-out dendritic neuron model (MODN) to tackle multi-output tasks. Our core idea is to introduce a filtering matrix to the soma layer to adaptively select the desired dendrites to regress each output. Because such a matrix is designed to be learnable, MODN can explore the relationship between each dendrite and output to provide a better solution to downstream tasks. We also model a telodendron layer into MODN to simulate better the real neuron behavior. Importantly, MODN is a more general and unified framework that can be naturally specialized as the DNM by customizing the filtering matrix. To explore the optimization of MODN, we investigate both heuristic and gradient-based optimizers and introduce a 2-step training method for MODN. Extensive experimental results performed on 11 datasets on both binary and multi-class classification tasks demonstrate the effectiveness of MODN, with respect to accuracy, convergence, and generality.