Self-organization of a recurrent RBF neural network using an information-oriented algorithm

被引：23
作者：
Han, Hong-Gui [1 ,2 ]
Guo, Ya-Nan [1 ,2 ]
Qiao, Jun-Fei [1 ,2 ]
机构：
[1] Beijing Univ Technol, Fac Informat Technol, Coll Automat, Beijing 100124, Peoples R China
[2] Beijing Key Lab Computat Intelligence & Intellige, Beijing 100124, Peoples R China
来源：
NEUROCOMPUTING | 2017年 / 225卷
基金：
美国国家科学基金会; 中国博士后科学基金;
关键词：
Information-oriented algorithm; Recurrent radial basis function neural network; Information processing strength; Component contributions; SEQUENTIAL LEARNING ALGORITHM; AUTOMATIC-GENERATION; PREDICTION; IDENTIFICATION;
D O I：
10.1016/j.neucom.2016.11.010
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper investigates how to construct a recurrent radial basis function neural network (RRBFNN) by an information-oriented algorithm (IOA) and how to adjust the parameters by a gradient algorithm simultaneously. In this IOA-based RRBFNN (IOA-RRBFNN), the proposed IOA is used to calculate the information processing strength (IPS) of hidden neurons, such that the independent component contributions between the hidden neurons and output neurons can be extracted. Then, a novel self-organizing strategy is proposed to optimize the structure of RRBFNN based on the input IPS and output IPS of hidden neurons. Meanwhile, a gradient algorithm is developed to update the parameters of IOA-RRBFNN. The proposed IOA-RRBFNN can be used to organize the network structure and adjust the parameters to improve its performance. Finally, several examples are presented to illustrate the effectiveness of IOA-RRBFNN. The results demonstrate that the proposed IOA-RRBFNN is more competitive in solving the nonlinear system modeling problems compared with some existing methods.
引用
收藏
页码：80 / 91
页数：12
相关论文
共 57 条
[1]   A neural network based linear ensemble framework for time series forecasting [J].
Adhikari, Ratnadip .
NEUROCOMPUTING, 2015, 157 :231-242
[2]  
[Anonymous], 2002, Advances in Neural Information Processing Systems
[3]   Self-organization of a recurrent network under ongoing synaptic plasticity [J].
Aoki, Takaaki .
NEURAL NETWORKS, 2015, 62 :11-19
[4]   Impulsive controller design for exponential synchronization of delayed stochastic memristor-based recurrent neural networks [J].
Chandrasekar, A. ;
Rakkiyappan, R. .
NEUROCOMPUTING, 2016, 173 :1348-1355
[5]   Online Modeling With Tunable RBF Network [J].
Chen, Hao ;
Gong, Yu ;
Hong, Xia .
IEEE TRANSACTIONS ON CYBERNETICS, 2013, 43 (03) :935-947
[6]   Time-series prediction using a local linear wavelet neural network [J].
Chen, YH ;
Yang, B ;
Dong, JW .
NEUROCOMPUTING, 2006, 69 (4-6) :449-465
[7]   TNFIS: Tree-Based Neural Fuzzy Inference System [J].
Cheu, Eng-Yeow ;
Quek, Hiok-Chai ;
Ng, See-Kiong .
2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8, 2008, :398-405
[8]   Recurrent neural network for approximate nonnegative matrix factorization [J].
Costantini, Giovanni ;
Perfetti, Renzo ;
Todisco, Massimiliano .
NEUROCOMPUTING, 2014, 138 :238-247
[9]  
Dhahri H., 2006, NEURAL NETW, V9
[10]   Adaptive hybrid control system using a recurrent RBFN-based self-evolving fuzzy-neural-network for PMSM servo drives [J].
El-Sousy, Fayez F. M. .
APPLIED SOFT COMPUTING, 2014, 21 :509-532
123456