Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
962 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS--I: FUNDAMENTAL THEORY AND APPLICATIONS, VOL. 46, NO. 8, AUGUST 1999 FPE-Based Criteria to Dimension
 

Summary: 962 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS--I: FUNDAMENTAL THEORY AND APPLICATIONS, VOL. 46, NO. 8, AUGUST 1999
FPE-Based Criteria to Dimension
Feedforward Neural Topologies
Cesare Alippi, Member, IEEE
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.
Index Terms-- FPE, learning from samples, model selection,
neural networks.

  

Source: Alippi, Cesare - Dipartimento di Elettronica e Informazione, Politecnico di Milano

 

Collections: Computer Technologies and Information Sciences