Visually Interpretable Fuzzy Neural Classification Network with Deep Convolutional Feature Maps

This paper proposes a deep feature map-based fuzzy neural classification network (DFM-FNCN) with applications to shape-based classification problems. The DFM-FNCN is characterized by compact and visually interpretable fuzzy if-then rules. Classification features in the DFM-FNCN are obtained from fea...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on fuzzy systems 2024-03, Vol.32 (3), p.1-15
Main Authors: Juang, Chia-Feng, Cheng, Yun-Wei, Lin, Yeh-Ming
Format: Article
Language:English
Subjects:
Algorithms
Artificial intelligence
Artificial neural networks
Classification
Convolutional neural networks
Decoding
deep learning
explainable AI
Feature extraction
Feature maps
Firing
fuzzy classifiers
Fuzzy logic
fuzzy neural networks
Image classification
interpretable fuzzy systems
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a deep feature map-based fuzzy neural classification network (DFM-FNCN) with applications to shape-based classification problems. The DFM-FNCN is characterized by compact and visually interpretable fuzzy if-then rules. Classification features in the DFM-FNCN are obtained from feature maps in a deep convolutional neural network (DCNN). The DFM-FNCN employs the divide-and-conquer technique, where a feature map-based fuzzification operation is proposed to find the firing strength of a fuzzy rule, to address the curse of dimensionality problem. The structure and parameters of the DFM-FNCN are learned through online rule generation and gradient descent algorithms, respectively. For visual interpretation of the learned fuzzy rules, this paper designs a deep decoder to map the antecedent of a fuzzy rule to an object-shaped image. The inference behavior of a fuzzy rule is interpreted by inspecting the relationship between the visualized antecedent and the classification levels of each class in the consequent. To speed up retraining of the DFM-FNCN in a new scenario, this paper proposes a method to select representative retraining images in a low-dimensional fuzzy rule-mapped space. The DFM-FNCN is applied to classify human postures and moving objects. Experimental results show the advantages of high classification accuracy, model interpretability, and retraining abilities of the DFM-FNCN.
ISSN:1063-6706
1941-0034
DOI:10.1109/TFUZZ.2023.3318086