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
N1 - Funding Information:
This work was financially supported by the “Chinese Language and Technology Center” of National Taiwan Normal University (NTNU) from The Featured Areas Research Center Program within the framework of the Higher Education Sprout Project by the Ministry of Education (MOE) in Taiwan, and Ministry of Science and Technology, Taiwan, under Grants no. MOST 108-2634-F-003-002 and MOST 108-2634-F-003-003 through Pervasive Artificial Intelligence Research (PAIR) Labs. We are grateful to the National Center for High-performance Computing for computer time and facilities to conduct this research.
Publisher Copyright:
© 2020, Taiwan Fuzzy Systems Association.
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
SN - 1562-2479
VL - 22
SP - 1
EP - 10
JO - International Journal of Fuzzy Systems
JF - International Journal of Fuzzy Systems
IS - 1
ER -