Dendritic Convolutional Neural Network

Rong Long Wang; Zhenyu Lei; Zhiming Zhang; Shangce Gao

doi:10.1002/tee.23513

Dendritic Convolutional Neural Network

Rong Long Wang, Zhenyu Lei, Zhiming Zhang, Shangce Gao^*

^*Corresponding author for this work

Intellectual Information Engineering

Research output: Contribution to journal › Letter › peer-review

18 Scopus citations

Abstract

Convolutional neural network (CNN), as one of the mainstream deep learning models, has achieved great success in image recognition. All neurons used in CNN are based on the McCulloch-Pitts model, which is over-simplified. To further improve CNN's learning capacity, this paper proposes a novel dendritic CNN (DCNN), which considers the nonlinear information processing functions of dendrites in a single neuron. The superiority of DCNN is confirmed based on four widely used image recognition tasks.

Original language	English
Pages (from-to)	302-304
Number of pages	3
Journal	IEEJ Transactions on Electrical and Electronic Engineering
Volume	17
Issue number	2
DOIs	https://doi.org/10.1002/tee.23513
State	Published - 2022/02

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.1002/tee.23513

Cite this

@article{21bb996f0ef04193bbe1b4e95f3b3e28,

title = "Dendritic Convolutional Neural Network",

abstract = "Convolutional neural network (CNN), as one of the mainstream deep learning models, has achieved great success in image recognition. All neurons used in CNN are based on the McCulloch-Pitts model, which is over-simplified. To further improve CNN's learning capacity, this paper proposes a novel dendritic CNN (DCNN), which considers the nonlinear information processing functions of dendrites in a single neuron. The superiority of DCNN is confirmed based on four widely used image recognition tasks.",

author = "Wang, {Rong Long} and Zhenyu Lei and Zhiming Zhang and Shangce Gao",

note = "Publisher Copyright: {\textcopyright} 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.",

year = "2022",

month = feb,

doi = "10.1002/tee.23513",

language = "英語",

volume = "17",

pages = "302--304",

journal = "IEEJ Transactions on Electrical and Electronic Engineering",

issn = "1931-4973",

publisher = "John Wiley & Sons Inc.",

number = "2",

}

TY - JOUR

T1 - Dendritic Convolutional Neural Network

AU - Wang, Rong Long

AU - Lei, Zhenyu

AU - Zhang, Zhiming

AU - Gao, Shangce

PY - 2022/2

Y1 - 2022/2

N2 - Convolutional neural network (CNN), as one of the mainstream deep learning models, has achieved great success in image recognition. All neurons used in CNN are based on the McCulloch-Pitts model, which is over-simplified. To further improve CNN's learning capacity, this paper proposes a novel dendritic CNN (DCNN), which considers the nonlinear information processing functions of dendrites in a single neuron. The superiority of DCNN is confirmed based on four widely used image recognition tasks.

AB - Convolutional neural network (CNN), as one of the mainstream deep learning models, has achieved great success in image recognition. All neurons used in CNN are based on the McCulloch-Pitts model, which is over-simplified. To further improve CNN's learning capacity, this paper proposes a novel dendritic CNN (DCNN), which considers the nonlinear information processing functions of dendrites in a single neuron. The superiority of DCNN is confirmed based on four widely used image recognition tasks.

UR - http://www.scopus.com/inward/record.url?scp=85117252497&partnerID=8YFLogxK

U2 - 10.1002/tee.23513

DO - 10.1002/tee.23513

M3 - Letter

AN - SCOPUS:85117252497

SN - 1931-4973

VL - 17

SP - 302

EP - 304

JO - IEEJ Transactions on Electrical and Electronic Engineering

JF - IEEJ Transactions on Electrical and Electronic Engineering

IS - 2

ER -

Dendritic Convolutional Neural Network

Abstract

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this