.png){kind=icon}
返回
Nonsingular Gradient Descent Algorithm for Interval Type-2 Fuzzy Neural Network
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2022.3225181.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
Convergence speed
interval type-2 fuzzy neural network (IT2FNN)
nonsingular gradient descent algorithm (NSGDA)
root inverse variance (RIV)
singularity
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
分享收藏
分享收藏Self-evolving function-link interval type-2 fuzzy neural network for nonlinear system identification and control.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Loss Allocation for Weakly Meshed Distribution System Using Analytical Formulation of Shapley Value
PREAI
分享收藏
查看更多内容