Paper Info
Title
Maximum likelihood neural approximation in presence of additive colored noise
Abstract
In many practical situations, the noise samples may be correlated. In this case, the estimation of noise parameters can be used to improve the approximation. Estimation of the noise structure can also be used to find a stopping criterion in constructive neural networks. To avoid overfitting, a network construction procedure must be stopped when residual can be considered as noise. The knowledge on the noise may be used for "whitening" the residual so that a correlation hypothesis test determines if the network growing must be continued or not. In this paper, supposing a Gaussian noise model, we study the problem of multi-output nonlinear regression using MLP when the noise in each output is a correlated autoregressive time series and is spatially correlated with other output noises. We show that the noise parameters can be determined simultaneously with the network weights and used to construct an estimator with a smaller variance, and so to improve the network generalization performance. Moreover, if a constructive procedure is used to build the network, the estimated parameters may be used to stop the procedure.
Year
DOI
Venue
2002
10.1109/72.977285
IEEE Transactions on Neural Networks
Keywords
Field
DocType
Gaussian noise,function approximation,generalisation (artificial intelligence),maximum likelihood estimation,multilayer perceptrons,Gaussian noise,additive colored noise,generalization,maximum likelihood estimation,multilayer perceptron,neural networks,nonlinear regression,parameter estimation
Autoregressive model,Value noise,Colors of noise,Noise measurement,Pattern recognition,Artificial intelligence,Overfitting,Stochastic resonance,Gaussian noise,Machine learning,Mathematics,Gradient noise
Journal
Volume
Issue
ISSN
13
1
1045-9227
Citations 
PageRank 
References 
3
0.60
14
Authors
2
Name
Order
Citations
PageRank
Shahram Hosseini118224.56
Christian Jutten245039.98