Nonsingular Gradient Descent Algorithm for Interval Type-2 Fuzzy Neural Network

Interval type-2 fuzzy neural network (IT2FNN) is widely used to model nonlinear systems. Unfortunately, the gradient descent-based IT2FNN with uncertain variances always suffers from low convergence speed due to its inherent singularity. To cope with this problem, a nonsingular gradient descent algo...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transaction on neural networks and learning systems Ročník 35; číslo 6; s. 8176 - 8189
Hlavní autoři: Han, Honggui, Sun, Chenxuan, Wu, Xiaolong, Yang, Hongyan, Qiao, Junfei
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.06.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Algorithms
Artificial neural networks
Convergence
Convergence speed
Fuzzy logic
Fuzzy neural networks
interval type-2 fuzzy neural network (IT2FNN)
Learning systems
Machine learning
Neural networks
Neurons
Nonlinear systems
nonsingular gradient descent algorithm (NSGDA)
Optimization
Oscillators
Parameters
root inverse variance (RIV)
singularity
Training
ISSN:2162-237X, 2162-2388, 2162-2388
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Interval type-2 fuzzy neural network (IT2FNN) is widely used to model nonlinear systems. Unfortunately, the gradient descent-based IT2FNN with uncertain variances always suffers from low convergence speed due to its inherent singularity. To cope with this problem, a nonsingular gradient descent algorithm (NSGDA) is developed to update IT2FNN in this article. First, the widths of type-2 fuzzy rules are transformed into root inverse variances (RIVs) that always satisfy the sufficient condition of differentiability. Second, the singular RIVs are reformulated by the nonsingular Shapley-based matrices associated with type-2 fuzzy rules. It averts the convergence stagnation caused by zero derivatives of singular RIVs, thereby sustaining the gradient convergence. Third, an integrated-form update strategy (IUS) is designed to obtain the derivatives of parameters, including RIVs, centers, weight coefficients, deviations, and proportionality coefficient of IT2FNN. These parameters are packed into multiple subvariable matrices, which are capable to accelerate gradient convergence using parallel calculation instead of sequence iteration. Finally, the experiments showcase that the proposed NSGDA-based IT2FNN can improve the convergence speed through the improved learning algorithm.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2162-237X
2162-2388
2162-2388
DOI:10.1109/TNNLS.2022.3225181