Improving Classification Performance in Dendritic Neuron Models through Practical Initialization Strategies

Document Type

Article

Publication Date

3-1-2024

Abstract

A dendritic neuron model (DNM) is a deep neural network model with a unique dendritic tree structure and activation function. Effective initialization of its model parameters is crucial for its learning performance. This work proposes a novel initialization method specifically designed to improve the performance of DNM in classifying high-dimensional data, notable for its simplicity, speed, and straightforward implementation. Extensive experiments on benchmark datasets show that the proposed method outperforms traditional and recent initialization methods, particularly in datasets consisting of high-dimensional data. In addition, valuable insights into the behavior of DNM during training and the impact of initialization on its learning performance are provided. This research contributes to the understanding of the initialization problem in deep learning and provides insights into the development of more effective initialization methods for other types of neural network models. The proposed initialization method can serve as a reference for future research on initialization techniques in deep learning.

Identifier

85189026157 (Scopus)

Publication Title

Sensors

External Full Text Location

https://doi.org/10.3390/s24061729

e-ISSN

14248220

PubMed ID

38543992

Issue

6

Volume

24

Grant

2023KY0055

This document is currently not available here.

Share

COinS