Assessing the noise immunity and generalization of radial basis function networks

被引：23

作者：

Bernier, JL ^{[1
]}

Díaz, AF ^{[1
]}

Fernández, FJ ^{[1
]}

Cañas, A ^{[1
]}

González, J ^{[1
]}

Martín-Smith, P ^{[1
]}

Ortega, J ^{[1
]}

机构：

[1] Univ Granada, Dept Arquitectura & Tecnol Comp, E-18071 Granada, Spain

来源：

NEURAL PROCESSING LETTERS | 2003年 / 18卷 / 01期

关键词：

generalization; Mean Square Error degradation; noise immunity; perturbation models; Radial Basis Function;

D O I：

10.1023/A:1026275522974

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In previous work we have derived a magnitude termed the 'Mean Squared Sensitivity' (MSS) to predict the performance degradation of a MLP affected by perturbations in different parameters. The present Letter continues the same line of researching, applying a similar methodology to deal with RBF networks and to study the implications when they are affected by input noise. We obtain the corresponding analytical expression for MSS in RBF networks and validate it experimentally, using two different models for perturbations: an additive and a multiplicative model. We discuss the relationship between MSS and the generalization ability. MSS is proposed as a quantitative measurement to evaluate the noise immunity and generalization ability of a RBFN configuration, giving even more generalization to our approach.

引用

下载

页码：35 / 48

页数：14

共 50 条

[21] Deferring the learning for better generalization in radial basis neural networks
Valls, JM
Isasi, P
Galván, IM
ARTIFICIAL NEURAL NETWORKS-ICANN 2001, PROCEEDINGS, 2001, 2130 : 189 - 195
[22] Radar target classification based on radial basis function and modified radial basis function networks
Liu, GS
Wang, YH
Yang, CL
Zhou, DQ
ICR '96 - 1996 CIE INTERNATIONAL CONFERENCE OF RADAR, PROCEEDINGS, 1996, : 208 - 211
[23] Function emulation using radial basis function networks
Chakravarthy, SV
Ghosh, J
NEURAL NETWORKS, 1997, 10 (03) : 459 - 478
[24] Comparison of generalization ability on solving differential equations using backpropagation and reformulated radial basis function networks
Choi, Bumghi
Lee, Ju-Hong
NEUROCOMPUTING, 2009, 73 (1-3) : 115 - 118
[25] Comparative study between radial basis probabilistic neural networks and radial basis function neural networks
Zhao, WB
Huang, DS
Guo, L
INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING, 2003, 2690 : 389 - 396
[26] Normalized Gaussian radial basis function networks
Bugmann, G
NEUROCOMPUTING, 1998, 20 (1-3) : 97 - 110
[27] Online learning in radial basis function networks
Freeman, JAS
Saad, D
NEURAL COMPUTATION, 1997, 9 (07) : 1601 - 1622
[28] Monotonic Normalized Radial Basis Function Networks
Husek, Petr
2019 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2019), 2019, : 3118 - 3123
[29] An Incremental Design of Radial Basis Function Networks
Yu, Hao
Reiner, Philip D.
Xie, Tiantian
Bartczak, Tomasz
Wilamowski, Bogdan M.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2014, 25 (10) : 1793 - 1803
[30] Monotonicity conditions for radial basis function networks
Husek, Petr
2018 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI), 2018, : 168 - 173

← 1 2 3 4 5 →