Radial Basis Function Networks with quantized parameters

被引：0
|
作者：
Lucks, Marcio B. [1 ]
Oki, Nobuo [1 ]
机构：
[1] Univ Estadual Paulista, Ilha Solteira, SP, Brazil
来源：
2008 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE FOR MEASUREMENT SYSTEMS AND APPLICATIONS | 2008年
关键词：
Radial Basis Function Network; quantized parameters; function approximation;
D O I：
10.1109/CIMSA.2008.4595826
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A RBFN implemented with quantized parameters is proposed and the relative or limited approximation property is presented. Simulation results for sinusoidal function approximation with various quantization levels are shown. The results indicate that the network presents good approximation capability even with severe quantization. The parameter quantization decreases the memory size and circuit complexity required to store the network parameters leading to compact mixed-signal circuits proper for low-power applications.
引用
收藏
页码：23 / 27
页数：5
相关论文
共 50 条
  • [41] Radial basis function networks and complexity regularization in function learning
    Krzyzak, A
    Linder, T
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (02): : 247 - 256
  • [42] Radial basis function networks in nonparametric classification and function learning
    Kegl, B
    Krzyzak, A
    Niemann, H
    [J]. FOURTEENTH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1 AND 2, 1998, : 565 - 570
  • [43] Nonlinear function learning by the normalized radial basis function networks
    Krzyzak, Adam
    Schaefer, Dominik
    [J]. ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING - ICAISC 2006, PROCEEDINGS, 2006, 4029 : 46 - 55
  • [44] Radial basis function networks and complexity regularization in function learning
    Krzyzak, A
    Linder, T
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 9: PROCEEDINGS OF THE 1996 CONFERENCE, 1997, 9 : 197 - 203
  • [45] Comparison of function approximation with sigmoid and radial basis function networks
    Russell, G
    Fausett, LV
    [J]. APPLICATIONS AND SCIENCE OF ARTIFICIAL NEURAL NETWORKS II, 1996, 2760 : 61 - 72
  • [46] Optimum design using radial basis function networks by adaptive range genetic algorithms - (Determination of radius in radial basis function networks)
    Arakawa, M
    Nakayama, H
    Yun, YB
    Ishikawa, H
    [J]. IECON 2000: 26TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1-4: 21ST CENTURY TECHNOLOGIES AND INDUSTRIAL OPPORTUNITIES, 2000, : 1219 - 1224
  • [47] The use of radial basis function networks (RBFN) to predict critical water parameters in desalination plants
    Riverol-Canizares, C.
    Pilipovik, V.
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2010, 37 (10) : 7285 - 7287
  • [48] Municipal Creditworthiness Modelling by Radial Basis Function Neural Networks and Sensitive Analysis of Their Input Parameters
    Olej, Vladimir
    Hajek, Petr
    [J]. ARTIFICIAL NEURAL NETWORKS - ICANN 2009, PT II, 2009, 5769 : 505 - 514
  • [49] Determining the structures and parameters of radial basis function neural networks using improved genetic algorithms
    Meiqin Liu
    Jida Chen
    [J]. Journal of Central South University of Technology, 1998, 5 (2): : 141 - 146
  • [50] Using radial basis function neural networks to recognize shifts in correlated manufacturing process parameters
    Cook, DF
    Chiu, CC
    [J]. IIE TRANSACTIONS, 1998, 30 (03) : 227 - 234
12345