Novel Sequential Neural Network Learning Algorithm for Function Approximation

被引：0

作者：

康怀祺

史彩成

何佩琨

李晓琼

机构：

[1] Beijing 100081 China

[2] School of Information Science and Technology Beijing Institute of Technology

[3] School of Information Science and Technology Beijing Institute of Technology

来源：

Journal of Beijing Institute of Technology | 2007年 / 02期

关键词：

sequential learning; predictor; proportional differential filter (PDF); neural network;

D O I：

10.15918/j.jbit1004-0579.2007.02.015

中图分类号：

TP183 [人工神经网络与计算];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A novel sequential neural network learning algorithm for function approximation is presented. The multi-step-ahead output predictor of the stochastic time series is introduced to the growing and pruning network for constructing network structure. And the network parameters are adjusted by the proportional differential filter (PDF) rather than EKF when the network growing criteria are not met. Experimental results show that the proposed algorithm can obtain a more compact network along with a smaller error in mean square sense than other typical sequential learning algorithms.

引用

页码：197 / 200

页数：4

共 50 条

[1] Novel sequential neural network learning algorithm for function approximation
Kang, Huai-Qi
Shi, Cai-Cheng
He, Pei-Kun
Li, Xiao-Qiong
[J]. Journal of Beijing Institute of Technology (English Edition), 2007, 16 (02): : 197 - 200
[2] A growing and pruning sequential learning algorithm of hyper basis function neural network for function approximation
Vukovic, Najdan
Miljkovic, Zoran
[J]. NEURAL NETWORKS, 2013, 46 : 210 - 226
[3] A constructive neural network algorithm for function approximation
Draelos, T
Hush, D
[J]. ICNN - 1996 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS. 1-4, 1996, : 50 - 55
[4] Algorithm for building a neural network for function approximation
Jayadeva
Deb, AK
Chandra, S
[J]. IEE PROCEEDINGS-CIRCUITS DEVICES AND SYSTEMS, 2002, 149 (5-6): : 301 - 307
[5] A new learning algorithm for function approximation by encoding additional constraints into feedforward neural network
Han, Fei
Ling, Qing-Hua
[J]. ADVANCED INTELLIGENT COMPUTING THEORIES AND APPLICATIONS: WITH ASPECTS OF CONTEMPORARY INTELLIGENT COMPUTING TECHNIQUES, 2007, 2 : 64 - +
[6] An Adaptive Fuzzy Wavelet Neural Network with Gradient Learning Algorithm For Nonlinear Function Approximation
Oysal, Yusuf
Yilmaz, Sevcan
[J]. 2013 10TH IEEE INTERNATIONAL CONFERENCE ON NETWORKING, SENSING AND CONTROL (ICNSC), 2013, : 152 - 157
[7] A novel machine learning algorithm for interval systems approximation based on artificial neural network
Zerrougui, Raouf
Adamou-Mitiche, Amel B. H.
Mitiche, Lahcene
[J]. JOURNAL OF INTELLIGENT MANUFACTURING, 2023, 34 (05) : 2171 - 2184
[8] A novel machine learning algorithm for interval systems approximation based on artificial neural network
Raouf Zerrougui
Amel B. H. Adamou-Mitiche
Lahcene Mitiche
[J]. Journal of Intelligent Manufacturing, 2023, 34 : 2171 - 2184
[9] Performance evaluation of a sequential minimal radial basis function (RBF) neural network learning algorithm
Lu, YW
Sundararajan, N
Saratchandran, P
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (02): : 308 - 318
[10] The Learning Algorithm for a Novel Fuzzy Neural Network
Liu, Puyin
Luo, Qiang
Yang, Wenqiang
Yi, Dongyun
[J]. INTELLIGENT COMPUTING, PART I: INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING, ICIC 2006, PART I, 2006, 4113 : 247 - 258

← 1 2 3 4 5 →