Pruning method for dendritic neuron model based on dendrite layer significance constraints

Document Type

Article

Publication Date

6-1-2023

Abstract

The dendritic neural model (DNM) mimics the non-linearity of synapses in the human brain to simulate the information processing mechanisms and procedures of neurons. This enhances the understanding of biological nervous systems and the applicability of the model in various fields. However, the existing DNM suffers from high complexity and limited generalisation capability. To address these issues, a DNM pruning method with dendrite layer significance constraints is proposed. This method not only evaluates the significance of dendrite layers but also allocates the significance of a few dendrite layers in the trained model to a few dendrite layers, allowing the removal of low-significance dendrite layers. The simulation experiments on six UCI datasets demonstrate that our method surpasses existing pruning methods in terms of network size and generalisation performance.

Identifier

85160725333 (Scopus)

Publication Title

Caai Transactions on Intelligence Technology

External Full Text Location

https://doi.org/10.1049/cit2.12234

e-ISSN

24682322

ISSN

24686557

First Page

308

Last Page

318

Issue

2

Volume

8

Grant

GXGZJG2020B101

Fund Ref

National Natural Science Foundation of China

This document is currently not available here.

Share

COinS