Prediction limit estimation for neural network models

被引：8

作者：

Chinnam, RB ^{[1
]}

Ding, J ^{[1
]}

机构：

[1] N Dakota State Univ, Dept Mfg Engn, Fargo, ND 58105 USA

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1998年 / 9卷 / 06期

关键词：

estimation; feedforward neural networks; prediction intervals; prediction limits; self-organizing feature maps;

D O I：

10.1109/72.728401

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A novel method for estimation of prediction limits for global and local approximating neural networks is presented. The method partitions the input space using self-organizing feature maps to introduce the concept of local neighborhoods, and calculates limits that indicate the extent to which one can rely on predictions for making future decisions.

引用

页码：1515 / 1522

页数：8

共 10 条

[1] Confidence interval prediction for neural network models
Chryssolouris, G
Lee, M
Ramsey, A
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (01): : 229 - 232
[2] DESIENO D, 1988, P IEEE INT C NEURAL, V1, P117
[3] Dougherty ER, 1990, PROBABILITY STAT ENG
[4] Haykin S., 1994, NEURAL NETWORKS COMP
[5] MULTILAYER FEEDFORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS
HORNIK, K
STINCHCOMBE, M
WHITE, H
[J]. NEURAL NETWORKS, 1989, 2 (05) : 359 - 366
[6] JOHNSTONE JK, 1994, MATH SURFACES, V5, P3
[7] SELF-ORGANIZED FORMATION OF TOPOLOGICALLY CORRECT FEATURE MAPS
KOHONEN, T
[J]. BIOLOGICAL CYBERNETICS, 1982, 43 (01) : 59 - 69
[8] THE SELF-ORGANIZING MAP
KOHONEN, T
[J]. PROCEEDINGS OF THE IEEE, 1990, 78 (09) : 1464 - 1480
[9] USING RADIAL BASIS FUNCTIONS TO APPROXIMATE A FUNCTION AND ITS ERROR-BOUNDS
LEONARD, JA
KRAMER, MA
UNGAR, LH
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (04): : 624 - 626
[10] Fast Learning in Networks of Locally-Tuned Processing Units
Moody, John
Darken, Christian J.
[J]. NEURAL COMPUTATION, 1989, 1 (02) : 281 - 294

← 1 →