当前位置: X-MOL 学术Appl. Soft Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Hierarchical polynomial-based fuzzy neural networks driven with the aid of hybrid network architecture and ranking-based neuron selection strategies
Applied Soft Computing ( IF 8.7 ) Pub Date : 2021-09-04 , DOI: 10.1016/j.asoc.2021.107865
Congcong Zhang 1 , Sung-Kwun Oh 2, 3 , Zunwei Fu 1, 3
Affiliation  

In this study, we propose hierarchical polynomial-based fuzzy neural networks (HPFNN). The aim of this study is to develop the design methodologies of hierarchical model to improve the prediction accuracy of the model without sacrificing computational efficiency through combining hybrid network architecture composed of different neurons and ranking-based neuron selection strategies. The essential bullets of the proposed model can be enumerated as follows: (a) A hybrid network architecture is designed by combining the traits of fuzzy rule-based neurons with random vector functional link (FRN-RVFL) and polynomial neurons. FRN-RVFL is employed to erect the first layer of network. The entire network topology and the neurons of the remaining layers are constructed with polynomial neural network. (b) Two kinds of ranking-based neuron selection (RNS) strategies such as Linear-RNS (LRNS) and Exponential-RNS (EPNS) are presented. Compared with traditional neuron selection strategy, RNS can enrich the diversity of candidate neurons while maintaining the approximation ability of neurons, which provides opportunities for selecting neurons with predictive potential. (c) Regularization-based least square approach is applied to alleviate the possible overfitting in coefficient estimation as well as enhance generalization abilities of the model. The performance of HPFNN is verified by using a series of synthetic data and machine learning datasets. Based on the experimental results, HPFNN exhibits sound prediction accuracy and reasonable computational cost in contrast with the same type of hierarchical models. Furthermore, HPFNN achieves better generalization performance on at least 12 of 20 datasets when compared with the performance of state-of-the-art models.



中文翻译:

借助混合网络架构和基于排序的神经元选择策略驱动的基于分层多项式的模糊神经网络

在这项研究中,我们提出了基于分层多项式的模糊神经网络(HPFNN)。本研究的目的是开发分层模型的设计方法,通过结合由不同神经元组成的混合网络架构和基于排序的神经元选择策略,在不牺牲计算效率的情况下提高模型的预测精度。所提出模型的基本要点可以列举如下:(a)通过将基于模糊规则的神经元与随机向量功能链接(FRN-RVFL)和多项式神经元的特征相结合,设计了混合网络架构。FRN-RVFL 用于架设网络的第一层。整个网络拓扑结构和其余层的神经元均采用多项式神经网络构建。(b) 提出了两种基于排序的神经元选择 (RNS) 策略,例如线性 RNS (LRNS) 和指数 RNS (EPNS)。与传统的神经元选择策略相比,RNS可以在保持神经元逼近能力的同时丰富候选神经元的多样性,为选择具有预测潜力的神经元提供了机会。(c) 应用基于正则化的最小二乘方法来减轻系数估计中可能的过度拟合并增强模型的泛化能力。HPFNN 的性能通过使用一系列合成数据和机器学习数据集进行验证。基于实验结果,与同类分层模型相比,HPFNN 表现出良好的预测精度和合理的计算成本。此外,

更新日期:2021-09-14
down
wechat
bug