The generalization complexity measure for continuous input data

Mostrar todas las versiones(2)

We introduce in this work an extension for the generalization complexity measure to continuous input data. The measure, originally defined in Boolean space, quantifies the complexity of data in relationship to the prediction accuracy that can be expected when using a supervised classifier like a neu...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Gómez, Iván, Cannas, Sergio Alejandro, Osenda, Omar, Jerez, José M., Franco, Leonardo
Formato: article
Lenguaje:Inglés
Publicado: 2021
Materias:
Complexity measure
Continuous input data
Acceso en línea:http://hdl.handle.net/11086/19897
http://dx.doi.org/10.1155/2014/815156
Aporte de:
Repositorio Digital Universitario (UNC) de Universidad Nacional de Córdoba
id I10-R141-11086-19897
record_format dspace
institution Universidad Nacional de Córdoba
institution_str I-10
repository_str R-141
collection Repositorio Digital Universitario (UNC)
language Inglés
topic Complexity measure
Continuous input data
spellingShingle Complexity measure
Continuous input data
Gómez, Iván
Cannas, Sergio Alejandro
Osenda, Omar
Jerez, José M.
Franco, Leonardo
The generalization complexity measure for continuous input data
topic_facet Complexity measure
Continuous input data
description We introduce in this work an extension for the generalization complexity measure to continuous input data. The measure, originally defined in Boolean space, quantifies the complexity of data in relationship to the prediction accuracy that can be expected when using a supervised classifier like a neural network, SVM, and so forth. We first extend the original measure for its use with continuous functions to later on, using an approach based on the use of the set of Walsh functions, consider the case of having a finite number of data points (inputs/outputs pairs), that is, usually the practical case. Using a set of trigonometric functions a model that gives a relationship between the size of the hidden layer of a neural network and the complexity is constructed. Finally, we demonstrate the application of the introduced complexity measure, by using the generated model, to the problem of estimating an adequate neural network architecture for real-world data sets.
format article
author Gómez, Iván
Cannas, Sergio Alejandro
Osenda, Omar
Jerez, José M.
Franco, Leonardo
author_facet Gómez, Iván
Cannas, Sergio Alejandro
Osenda, Omar
Jerez, José M.
Franco, Leonardo
author_sort Gómez, Iván
title The generalization complexity measure for continuous input data
title_short The generalization complexity measure for continuous input data
title_full The generalization complexity measure for continuous input data
title_fullStr The generalization complexity measure for continuous input data
title_full_unstemmed The generalization complexity measure for continuous input data
title_sort generalization complexity measure for continuous input data
publishDate 2021
url http://hdl.handle.net/11086/19897
http://dx.doi.org/10.1155/2014/815156
work_keys_str_mv AT gomezivan thegeneralizationcomplexitymeasureforcontinuousinputdata
AT cannassergioalejandro thegeneralizationcomplexitymeasureforcontinuousinputdata
AT osendaomar thegeneralizationcomplexitymeasureforcontinuousinputdata
AT jerezjosem thegeneralizationcomplexitymeasureforcontinuousinputdata
AT francoleonardo thegeneralizationcomplexitymeasureforcontinuousinputdata
AT gomezivan generalizationcomplexitymeasureforcontinuousinputdata
AT cannassergioalejandro generalizationcomplexitymeasureforcontinuousinputdata
AT osendaomar generalizationcomplexitymeasureforcontinuousinputdata
AT jerezjosem generalizationcomplexitymeasureforcontinuousinputdata
AT francoleonardo generalizationcomplexitymeasureforcontinuousinputdata
bdutipo_str Repositorios
_version_ 1764820391865352193

Ejemplares similares