A Convolutional Fuzzy Neural Network Architecture for Object Classification with Small Training Database

Min Jie Hsu, Yi Hsing Chien, Wei Yen Wang, Chen Chien Hsu

Research output: Contribution to journalArticle

Abstract

In this paper, we propose a novel architecture that combines the convolutional neural network (CNN) with a fuzzy neural network (FNN). We utilize the fuzzy neural network with semi-connected layers to sum up feature information. During the training process, to map membership values, the CNN generates feature maps as outputs and feeds into fuzzifier layers, alternatively called fuzzy maps. The proposed method increases classification accuracy, because fuzzy neural networks can generate not only crisp values but also fuzzy values; this means that there is potentially more information contained in the fuzzy set. Our model is evaluated by cross-validation tests. While big data is necessary for training in general, we train our model with small data and test with big data to demonstrate its ability of object classification in cases where sufficient data are not available.

Original languageEnglish
JournalInternational Journal of Fuzzy Systems
Volume22
Issue number1
DOIs
Publication statusPublished - 2020 Feb 1

Fingerprint

Object Classification
Fuzzy neural networks
Fuzzy Neural Network
Network Architecture
Network architecture
Neural networks
Neural Networks
Fuzzy sets
Cross-validation
Fuzzy Sets
Sufficient
Necessary
Training
Output
Model
Demonstrate
Big data

Keywords

  • Convolutional neural network
  • Fuzzy neural network
  • Object classification
  • Small data

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Computational Theory and Mathematics
  • Artificial Intelligence

Cite this

A Convolutional Fuzzy Neural Network Architecture for Object Classification with Small Training Database. / Hsu, Min Jie; Chien, Yi Hsing; Wang, Wei Yen; Hsu, Chen Chien.

In: International Journal of Fuzzy Systems, Vol. 22, No. 1, 01.02.2020.

Research output: Contribution to journalArticle

@article{136c8fb6a44c404a9283cb335ee6d307,
title = "A Convolutional Fuzzy Neural Network Architecture for Object Classification with Small Training Database",
abstract = "In this paper, we propose a novel architecture that combines the convolutional neural network (CNN) with a fuzzy neural network (FNN). We utilize the fuzzy neural network with semi-connected layers to sum up feature information. During the training process, to map membership values, the CNN generates feature maps as outputs and feeds into fuzzifier layers, alternatively called fuzzy maps. The proposed method increases classification accuracy, because fuzzy neural networks can generate not only crisp values but also fuzzy values; this means that there is potentially more information contained in the fuzzy set. Our model is evaluated by cross-validation tests. While big data is necessary for training in general, we train our model with small data and test with big data to demonstrate its ability of object classification in cases where sufficient data are not available.",
keywords = "Convolutional neural network, Fuzzy neural network, Object classification, Small data",
author = "Hsu, {Min Jie} and Chien, {Yi Hsing} and Wang, {Wei Yen} and Hsu, {Chen Chien}",
year = "2020",
month = "2",
day = "1",
doi = "10.1007/s40815-019-00764-1",
language = "English",
volume = "22",
journal = "International Journal of Fuzzy Systems",
issn = "1562-2479",
publisher = "Chinese Fuzzy Systems Association",
number = "1",

}

TY - JOUR

T1 - A Convolutional Fuzzy Neural Network Architecture for Object Classification with Small Training Database

AU - Hsu, Min Jie

AU - Chien, Yi Hsing

AU - Wang, Wei Yen

AU - Hsu, Chen Chien

PY - 2020/2/1

Y1 - 2020/2/1

N2 - In this paper, we propose a novel architecture that combines the convolutional neural network (CNN) with a fuzzy neural network (FNN). We utilize the fuzzy neural network with semi-connected layers to sum up feature information. During the training process, to map membership values, the CNN generates feature maps as outputs and feeds into fuzzifier layers, alternatively called fuzzy maps. The proposed method increases classification accuracy, because fuzzy neural networks can generate not only crisp values but also fuzzy values; this means that there is potentially more information contained in the fuzzy set. Our model is evaluated by cross-validation tests. While big data is necessary for training in general, we train our model with small data and test with big data to demonstrate its ability of object classification in cases where sufficient data are not available.

AB - In this paper, we propose a novel architecture that combines the convolutional neural network (CNN) with a fuzzy neural network (FNN). We utilize the fuzzy neural network with semi-connected layers to sum up feature information. During the training process, to map membership values, the CNN generates feature maps as outputs and feeds into fuzzifier layers, alternatively called fuzzy maps. The proposed method increases classification accuracy, because fuzzy neural networks can generate not only crisp values but also fuzzy values; this means that there is potentially more information contained in the fuzzy set. Our model is evaluated by cross-validation tests. While big data is necessary for training in general, we train our model with small data and test with big data to demonstrate its ability of object classification in cases where sufficient data are not available.

KW - Convolutional neural network

KW - Fuzzy neural network

KW - Object classification

KW - Small data

UR - http://www.scopus.com/inward/record.url?scp=85077607884&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077607884&partnerID=8YFLogxK

U2 - 10.1007/s40815-019-00764-1

DO - 10.1007/s40815-019-00764-1

M3 - Article

AN - SCOPUS:85077607884

VL - 22

JO - International Journal of Fuzzy Systems

JF - International Journal of Fuzzy Systems

SN - 1562-2479

IS - 1

ER -