The Generalization Complexity Measure for Continuous Input Data
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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-01-01
|
| Series: | The Scientific World Journal |
| Online Access: | http://dx.doi.org/10.1155/2014/815156 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832551857349722112 |
|---|---|
| author | Iván Gómez Sergio A. Cannas Omar Osenda José M. Jerez Leonardo Franco |
| author_facet | Iván Gómez Sergio A. Cannas Omar Osenda José M. Jerez Leonardo Franco |
| author_sort | Iván Gómez |
| collection | DOAJ |
| 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 |
| id | doaj-art-12fb32b483634814ba09b952895ee632 |
| institution | Kabale University |
| issn | 2356-6140 1537-744X |
| language | English |
| publishDate | 2014-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | The Scientific World Journal |
| spelling | doaj-art-12fb32b483634814ba09b952895ee6322025-02-03T06:00:08ZengWileyThe Scientific World Journal2356-61401537-744X2014-01-01201410.1155/2014/815156815156The Generalization Complexity Measure for Continuous Input DataIván Gómez0Sergio A. Cannas1Omar Osenda2José M. Jerez3Leonardo Franco4Departamento de Lenguajes y Ciencias de la Computación, Universidad de Málaga, 29071 Málaga, SpainFacultad de Matemática, Astronomía y Física, Universidad Nacional de Córdoba, 5000 Córdoba, ArgentinaFacultad de Matemática, Astronomía y Física, Universidad Nacional de Córdoba, 5000 Córdoba, ArgentinaDepartamento de Lenguajes y Ciencias de la Computación, Universidad de Málaga, 29071 Málaga, SpainDepartamento de Lenguajes y Ciencias de la Computación, Universidad de Málaga, 29071 Málaga, SpainWe 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.http://dx.doi.org/10.1155/2014/815156 |
| spellingShingle | Iván Gómez Sergio A. Cannas Omar Osenda José M. Jerez Leonardo Franco The Generalization Complexity Measure for Continuous Input Data The Scientific World Journal |
| title | 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_short | The Generalization Complexity Measure for
Continuous Input Data |
| title_sort | generalization complexity measure for continuous input data |
| url | http://dx.doi.org/10.1155/2014/815156 |
| work_keys_str_mv | AT ivangomez thegeneralizationcomplexitymeasureforcontinuousinputdata AT sergioacannas thegeneralizationcomplexitymeasureforcontinuousinputdata AT omarosenda thegeneralizationcomplexitymeasureforcontinuousinputdata AT josemjerez thegeneralizationcomplexitymeasureforcontinuousinputdata AT leonardofranco thegeneralizationcomplexitymeasureforcontinuousinputdata AT ivangomez generalizationcomplexitymeasureforcontinuousinputdata AT sergioacannas generalizationcomplexitymeasureforcontinuousinputdata AT omarosenda generalizationcomplexitymeasureforcontinuousinputdata AT josemjerez generalizationcomplexitymeasureforcontinuousinputdata AT leonardofranco generalizationcomplexitymeasureforcontinuousinputdata |