Robust Fuzzy Neural Network With an Adaptive Inference Engine.

Zhang, L; Shi, Y; Chang, Y-C; Lin, C-T

Robust Fuzzy Neural Network With an Adaptive Inference Engine.

Zhang, L

Shi, Y Chang, Y-C Lin, C-T

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Trans Cybern, 2023, PP, (99)
Issue Date:: 2023-02-15

Embargoed

	Filename	Description	Size
	Robust Fuzzy Neural Network With an Adaptive Inference Engine.pdf	Accepted version	548.85 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Embargoed
Open Access

This item is currently unavailable due to the publisher's embargo.

The embargo period expires on 15 Feb 2025

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, L https://orcid.org/0000-0001-5126-1778
dc.contributor.author	Shi, Y
dc.contributor.author	Chang, Y-C
dc.contributor.author	Lin, C-T
dc.date.accessioned	2024-03-05T03:45:32Z
dc.date.available	2024-03-05T03:45:32Z
dc.date.issued	2023-02-15
dc.identifier.citation	IEEE Trans Cybern, 2023, PP, (99)
dc.identifier.issn	2168-2267
dc.identifier.issn	2168-2275
dc.identifier.uri	http://hdl.handle.net/10453/176125
dc.description.abstract	Fuzzy neural networks (FNNs) have been very successful at handling uncertainty in data using fuzzy mappings and if-then rules. However, they suffer from generalization and dimensionality issues. Although deep neural networks (DNNs) represent a step toward processing high-dimensional data, their capacity to address data uncertainty is limited. Furthermore, deep learning algorithms designed to improve robustness are either time consuming or yield unsatisfactory performance. In this article, we propose a robust fuzzy neural network (RFNN) to overcome these problems. The network contains an adaptive inference engine that is capable of handling samples with high-level uncertainty and high dimensions. Unlike traditional FNNs that use a fuzzy AND operation to calculate the firing strength for each rule, our inference engine is able to learn the firing strength adaptively. It also further processes the uncertainty in membership function values. Taking advantage of the learning ability of neural networks, the acquired fuzzy sets can be learned from training inputs automatically to cover the input space well. Furthermore, the consequent layer uses neural network structures to enhance the reasoning ability of the fuzzy rules when dealing with complex inputs. Experiments on a range of datasets show that RFNN delivers state-of-the-art accuracy even at very high levels of uncertainty. Our code is available online. https://github.com/leijiezhang/RFNN.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation	http://purl.org/au-research/grants/arc/DP210101093
dc.relation	http://purl.org/au-research/grants/arc/DP220100803
dc.relation.ispartof	IEEE Trans Cybern
dc.relation.isbasedon	10.1109/TCYB.2023.3241170
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.title	Robust Fuzzy Neural Network With an Adaptive Inference Engine.
dc.type	Journal Article
utslib.citation.volume	PP
utslib.location.activity	United States
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	embargoed	*
utslib.copyright.embargo	2025-02-15T00:00:00+1000Z
dc.date.updated	2024-03-05T03:45:30Z
pubs.issue	99
pubs.publication-status	Published online
pubs.volume	PP
utslib.citation.issue	99

Abstract:

Fuzzy neural networks (FNNs) have been very successful at handling uncertainty in data using fuzzy mappings and if-then rules. However, they suffer from generalization and dimensionality issues. Although deep neural networks (DNNs) represent a step toward processing high-dimensional data, their capacity to address data uncertainty is limited. Furthermore, deep learning algorithms designed to improve robustness are either time consuming or yield unsatisfactory performance. In this article, we propose a robust fuzzy neural network (RFNN) to overcome these problems. The network contains an adaptive inference engine that is capable of handling samples with high-level uncertainty and high dimensions. Unlike traditional FNNs that use a fuzzy AND operation to calculate the firing strength for each rule, our inference engine is able to learn the firing strength adaptively. It also further processes the uncertainty in membership function values. Taking advantage of the learning ability of neural networks, the acquired fuzzy sets can be learned from training inputs automatically to cover the input space well. Furthermore, the consequent layer uses neural network structures to enhance the reasoning ability of the fuzzy rules when dealing with complex inputs. Experiments on a range of datasets show that RFNN delivers state-of-the-art accuracy even at very high levels of uncertainty. Our code is available online. https://github.com/leijiezhang/RFNN.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/176125