Assessing the Noise Immunity and Generalization of Radial Basis Function Networks

Authors:
J. L. Bernier;A. F. Díaz;F. J. Fernández;A. Cañas;J. González;P. Martín-Smith;J. Ortega
Affiliations:
Depto. Arquitectura y Tecnología de Computadores, Universidad de Granada, E18071-Granada, Spain. e-mail: jbernier@atc.ugr.es;Depto. Arquitectura y Tecnología de Computadores, Universidad de Granada, E18071-Granada, Spain;Depto. Arquitectura y Tecnología de Computadores, Universidad de Granada, E18071-Granada, Spain;Depto. Arquitectura y Tecnología de Computadores, Universidad de Granada, E18071-Granada, Spain;Depto. Arquitectura y Tecnología de Computadores, Universidad de Granada, E18071-Granada, Spain;Depto. Arquitectura y Tecnología de Computadores, Universidad de Granada, E18071-Granada, Spain;Depto. Arquitectura y Tecnología de Computadores, Universidad de Granada, E18071-Granada, Spain
Venue:
Neural Processing Letters
Year:
2003

Citing 14
Cited 5

Perturbation response in feedforward networks

Neural Networks
Training with noise is equivalent to Tikhonov regularization

Neural Computation
Flat minima

Neural Computation
Toward optimally distributed computation

Neural Computation
An Accurate Measure for Multilayer Perceptron Tolerance to Weight Deviations

Neural Processing Letters
An efficient learning algorithm for improving generalization performance of radial basis function neural networks

Neural Networks
Obtaining Fault Tolerant Multilayer Perceptrons Using an Explicit Regularization

Neural Processing Letters
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Upper bound of the expected training error of neural network regression for a Gaussian noise sequence

Neural Networks
Time Series Analysis, Forecasting and Control

Time Series Analysis, Forecasting and Control
A Quantitative Study of Fault Tolerance, Noise Immunity, and Generalization Ability of MLPs

Neural Computation
Comparison of adaptive methods for function estimation from samples

IEEE Transactions on Neural Networks
Estimations of error bounds for neural-network function approximators

IEEE Transactions on Neural Networks
Multiobjective evolutionary optimization of the size, shape, and position parameters of radial basis function networks for function approximation

IEEE Transactions on Neural Networks

Analysis on Bidirectional Associative Memories with Multiplicative Weight Noise

Neural Information Processing
On objective function, regularizer, and prediction error of a learning algorithm for dealing with multiplicative weight noise

IEEE Transactions on Neural Networks
Convergence and objective functions of some fault/noise-injection-based online learning algorithms for RBF networks

IEEE Transactions on Neural Networks
Kernel Width Optimization for Faulty RBF Neural Networks with Multi-node Open Fault

Neural Processing Letters
Pareto-optimal noise and approximation properties of RBF networks

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.