FPE-based criteria to dimension feedforward neural topologies

Author

Alippi, Cesare

Author_Institution

Dipt. di Elettronica, Politecnico di Milano, Italy

Volume

46

Issue

8

fYear

1999

fDate

8/1/1999 12:00:00 AM

Firstpage

962

Lastpage

973

Abstract

This paper deals with the problem of dimensioning a feedforward neural network to learn an unknown function from input/output pairs. The ultimate goal is to tune the complexity of the neural model with the information present in the training set and to estimate its performance without needing new data for cross-validation. For generality, it is not assumed that the unknown function belongs to the family of neural models. A generalization of the final prediction error to biased models is provided, which can be applied to learn unknown functions both in noise free and noise affected applications. This is based on a new definition of the effective number of parameters used by the neural model to fit the data. New criteria for model selection are introduced and compared with the generalized prediction error and the network information criteria

Keywords

feedforward neural nets; learning (artificial intelligence); prediction theory; FPE-based criteria; biased models; dimensioning; feedforward neural topologies; final prediction error; input/output pairs; model selection; network information criteria; neural model complexity; training set; unknown function; unknown functions; Biological neural networks; Covariance matrix; Feedforward neural networks; Gaussian processes; Network topology; Neural networks; Neurons; Predictive models; Surges; Training data;

fLanguage

English

Journal_Title

Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on

Publisher

ieee

ISSN

1057-7122

Type

jour

DOI

10.1109/81.780377

Filename

780377