Adaptive regression estimation with multilayer feedforward neural networks

被引：23
|
作者：
Kohler, M
Krzyzak, A
机构：
[1] Concordia Univ, Dept Comp Sci & Software Engn, Montreal, PQ H3G 1M8, Canada
[2] Univ Saarland, Fachrichtung Math 6 1, D-66041 Saarbrucken, Germany
来源：
JOURNAL OF NONPARAMETRIC STATISTICS | 2005年 / 17卷 / 08期
基金：
加拿大自然科学与工程研究理事会;
关键词：
multilayer neural networks; nonparametric regression; complexity regularization; additive regression;
D O I：
10.1080/10485250500309608
中图分类号：
O21 [概率论与数理统计]; C8 [统计学];
学科分类号：
020208 ; 070103 ; 0714 ;
摘要：
We prove a general bound on the expected L-2 error of adaptive least squares estimates. By applying it to multilayer feedforward neural network regression function estimates, we are able to obtain fast rates of convergence in special classes of regression functions such as additive functions.
引用
收藏
页码：891 / 913
页数：23
相关论文
共 50 条
  • [1] Adaptive regression estimation with multilayer feedforward neural networks
    Kohler, M
    Krzyzak, A
    [J]. 2004 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY, PROCEEDINGS, 2004, : 467 - 467
  • [2] An adaptive activation function for multilayer feedforward neural networks
    Yu, CC
    Tang, YC
    Liu, BD
    [J]. 2002 IEEE REGION 10 CONFERENCE ON COMPUTERS, COMMUNICATIONS, CONTROL AND POWER ENGINEERING, VOLS I-III, PROCEEDINGS, 2002, : 645 - 650
  • [3] EAST: An Exponential Adaptive Skipping Training algorithm for multilayer feedforward neural networks
    Department of Computer Science and Engineering, Kongu Engineering College, Perundurai, Erode
    638 052, India
    不详
    638 052, India
    [J]. WSEAS Trans. Comput., (138-151):
  • [4] METHODS FOR ENCODING IN MULTILAYER FEEDFORWARD NEURAL NETWORKS
    ELIZALDE, E
    GOMEZ, S
    ROMEO, A
    [J]. LECTURE NOTES IN COMPUTER SCIENCE, 1991, 540 : 136 - 143
  • [5] Applications of multilayer feedforward neural networks in electrogastrography
    Medical Cent Oklahoma City, Oklahoma City, United States
    [J]. Biomed Eng Appl Basis Commun, 6 (594-611):
  • [6] ROBUSTNESS OF REPRESENTATIONS IN MULTILAYER FEEDFORWARD NEURAL NETWORKS
    DIAMOND, P
    FOMENKO, IV
    [J]. CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 1993, 12 (02) : 211 - 221
  • [7] Adaptive Control of Antilock Braking System Using Grey Multilayer Feedforward Neural Networks
    Kayacan, Erdal
    Oniz, Yesim
    Kaynak, Okyay
    Topalov, Andon V.
    [J]. SEVENTH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, PROCEEDINGS, 2008, : 356 - 361
  • [8] Sliding mode strategy for adaptive learning in multilayer feedforward neural networks with a scalar output
    Topalov, AV
    Kaynak, O
    [J]. 2003 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOLS 1-5, CONFERENCE PROCEEDINGS, 2003, : 1636 - 1641
  • [9] Application of multilayer feedforward neural networks to precipitation cell-top altitude estimation
    Spina, MS
    Schwartz, MJ
    Staelin, DH
    Gasiewski, AJ
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1998, 36 (01): : 154 - 162
  • [10] Multilayer feedforward networks with adaptive spline activation function
    Guarnieri, S
    Piazza, F
    Uncini, A
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (03): : 672 - 683
12345