Adaptive receptive fields for radial basis functions

被引:18
|
作者
Jafar, MM [1 ]
Zilouchian, A [1 ]
机构
[1] Florida Atlantic Univ, Dept Elect Engn, Boca Raton, FL 33431 USA
关键词
reverse osmosis; neural network; prediction; radial basis function network;
D O I
10.1016/S0011-9164(01)00141-2
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
We propose a network architecture based on adaptive receptive fields and a learning algorithm that combines both supervised learning of centers and unsupervised learning of output layer weights. This algorithm causes each group of radial basis functions to adapt to regions of the clustered input space. Networks produced by this algorithm appear to have better generalization performance on prediction of non-linear input-output mappings than corresponding backpropagation algorithms and requires a fraction of the number of connection weights required by fixed center radial basis. For a test problem of predicting product quality of a reverse osmosis desalination plant, the network learns much faster than a three-layer perceptron trained with back-propagation, but requires additional computational burden.
引用
收藏
页码:83 / 91
页数:9
相关论文
共 50 条
  • [1] NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions
    Chen, Zhang
    Li, Zhong
    Song, Liangchen
    Chen, Lele
    Yu, Jingyi
    Yuan, Junsong
    Xu, Yi
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 4159 - 4171
  • [2] Image interpolation with adaptive receptive field-based Gaussian radial basis functions
    Ahmed, F
    Gustafson, SC
    Karim, MA
    MICROWAVE AND OPTICAL TECHNOLOGY LETTERS, 1996, 13 (04) : 197 - 202
  • [3] Evolving basis functions with dynamic receptive fields
    Angeline, PJ
    SMC '97 CONFERENCE PROCEEDINGS - 1997 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-5: CONFERENCE THEME: COMPUTATIONAL CYBERNETICS AND SIMULATION, 1997, : 4109 - 4114
  • [4] Shape-adaptive radial basis functions
    Webb, AR
    Shannon, S
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (06): : 1155 - 1166
  • [5] Reconstruction of Corrupted Vector Fields using Radial Basis Functions
    Smolik, Michal
    Skala, Vaclav
    2019 IEEE 15TH INTERNATIONAL SCIENTIFIC CONFERENCE ON INFORMATICS (INFORMATICS 2019), 2019, : 377 - 382
  • [6] Node Adaptive Domain Decomposition Method by Radial Basis Functions
    Gonzalez-Casanova, Pedro
    Antonio Munoz-Gomez, Jose
    Rodriguez-Gomez, Gustavo
    NUMERICAL METHODS FOR PARTIAL DIFFERENTIAL EQUATIONS, 2009, 25 (06) : 1482 - 1501
  • [7] Adaptive Methods for Analysis of Composite Plates with Radial Basis Functions
    Neves, A. M. A.
    Driscoll, T. A.
    Heryudono, A. R. H.
    Ferreira, A. J. M.
    Soares, C. M. M.
    Jorge, R. M. N.
    MECHANICS OF ADVANCED MATERIALS AND STRUCTURES, 2011, 18 (06) : 420 - 430
  • [8] Adaptive transfer functions in radial basis function (RBF) networks
    Hoffmann, GA
    COMPUTATIONAL SCIENCE - ICCS 2004, PT 2, PROCEEDINGS, 2004, 3037 : 682 - 686
  • [9] Representation of complex optical surfaces with adaptive radial basis functions
    Zhou, Xiangdong
    Huang, Xiao
    Bai, Jian
    Zhao, Lei
    Hou, Jing
    Wang, Kaiwei
    Hua, Yongxiao
    APPLIED OPTICS, 2019, 58 (14) : 3938 - 3944
  • [10] Compactly supported radial basis functions for adaptive process control
    Pottmann, M
    Henson, MA
    JOURNAL OF PROCESS CONTROL, 1997, 7 (05) : 345 - 356