arrow
Return

BPFNN: Bayesian Probabilistic Fuzzy Neural Networks for Uncertainty-Aware Clustering and Probabilistic Fuzzy Reasoning

delete2025-10-28
delete0
PRE
AI
朱
朱云龙 (Yunlong Zhu)
段
段海滨 (Haibin Duan)
Z
Zheng Wang
E
Eun-Hu Kim
Z
Zunwei Fu
W
Witold Pedrycz
DOI:10.1109/TCYB.2025.3617987delete
deleteOriginal
deleteShare
deleteSave
Abstract

Abstract

En 中文
This article introduces the Bayesian probabilistic fuzzy neural network (BPFNN), a unified architecture designed to overcome the challenges of conventional fuzzy clustering and neural networks in terms of uncertainty, noise, and interpretability. At its core, the Bayesian probabilistic fuzzy $C$ -means (BPFCMs) algorithm is employed to define the hidden-layer nodes, extending traditional FCM through non-Gaussian modeling and posterior inference via Markov chain Monte Carlo (MCMC). By combining Metropolis–Hastings (MHs) for membership updates with Gibbs sampling for parameter estimation, BPFCM yields probabilistic memberships that capture uncertainty in the antecedent rules more effectively than deterministic approaches. Since the hidden-layer activations represent only similarity values between inputs and cluster centers, the original input features are not directly preserved. To compensate, the hidden-to-output connections are formulated as linear functions of the input, ensuring recovery of discriminative information in the consequent rules. These functions are optimized using a generalized cross-entropy (GCE) objective, with iteratively reweighted least squares (IRLSs) employed for efficient and regularized updates. Extensive experiments on benchmark datasets and high-dimensional laser-induced breakdown spectroscopy (LIBS) spectral data confirm that BPFNN consistently surpasses both classical fuzzy systems and contemporary deep learning models, providing improved accuracy, robustness, and interpretability.
Keywords:
Bayesian probability
fuzzy clustering
iteratively reweighted least squares (IRLSs)
Markov chain Monte Carlo (MCMC)
Metropolis–Hastings (MHs) algorithm

Journal

IEEE Transactions on Cybernetics cover
IEEE Transactions on Cybernetics
IF:
10.5
Papers:
1.1W
Citations:
5.0W

Organization

B
beihang university
Scholars:
5.2K
Papers: 2.0K
Citations: 21
U
university of alberta
Scholars:
5.1W
Papers: 4.9W
Citations: 65
L
linyi university
Scholars:
4.4K
Papers: 3.2K
Citations: 62
researcher View more organizations
Cited Papers

Cited Papers

Fuzzy neural networks: A survey
err1994-08-01
err0
PREAI
errJames J. Buckley; Yoichi Hayashi
errShare
errSave
A Hybrid Learning Method for Constructing Compact Rule-Based Fuzzy Models
err2013-12-01
err17
PREAI
errZhao, Wanqing; Niu, Qun; Li, Kang; Irwin, George W.
errShare
errSave
Feed-Forward Neural Networks
err2021-04-10
err0
PREAI
errNikhil Ketkar; Jojo Moolayil
errShare
errSave
errShare
errSave
err
IF0
err
err0
PREAI
err
errShare
errSave
researcher View more