• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Ou, Jun (Ou, Jun.) | Li, Yujian (Li, Yujian.) | Shan, Chuanhui (Shan, Chuanhui.)

Indexed by:

EI Scopus SCIE

Abstract:

Convolutional neural networks (CNNs) have made remarkable success in image classification. However, it is still an open problem how to develop new models instead of CNNs. Here, we propose a novel model, namely two-dimensional perceptron (TDP), to get direct input of 2D data for further processing. A TDP computes hidden neurons from the input via left/right matrix multiplication, producing left-weighted TDP and right-weighted TDP, respectively. Experimental results on MNIST and COIL-20 datasets show that, in cases with the same number of hidden neurons, the model obtains 5%-45% relative performance improvement and 2 x-36x speedup in comparison with the corresponding multilayer perceptron and convolutional neural network. Hence, it is a promising and potential model that may open some new directions for deep neural networks, particularly alternatives to CNNs.

Keyword:

Left weight matrix Right weight matrix Multilayer perceptron Neural networks Two-dimensional perceptron

Author Community:

  • [ 1 ] [Ou, Jun]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 2 ] [Li, Yujian]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 3 ] [Shan, Chuanhui]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 4 ] [Li, Yujian]Guilin Univ Elect Technol, Sch Artificial Intelligence, Guilin 541004, Peoples R China

Reprint Author's Address:

  • [Ou, Jun]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China

Show more details

Related Keywords:

Related Article:

Source :

SOFT COMPUTING

ISSN: 1432-7643

Year: 2020

Issue: 5

Volume: 24

Page: 3355-3364

4 . 1 0 0

JCR@2022

ESI Discipline: COMPUTER SCIENCE;

ESI HC Threshold:132

Cited Count:

WoS CC Cited Count: 3

SCOPUS Cited Count: 3

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 2

Affiliated Colleges:

Online/Total:637/5296211
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.