The Generalization Complexity Measure for Continuous Input Data
Joint Authors
Jerez, José M.
Gómez, Iván
Cannas, Sergio A.
Osenda, Omar
Franco, Leonardo
Source
Issue
Vol. 2014, Issue 2014 (31 Dec. 2014), pp.1-9, 9 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2014-04-10
Country of Publication
Egypt
No. of Pages
9
Main Subjects
Medicine
Information Technology and Computer Science
Abstract EN
We introduce in this work an extension for the generalization complexity measure to continuous input data.
The measure, originallydefined 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.
American Psychological Association (APA)
Gómez, Iván& Cannas, Sergio A.& Osenda, Omar& Jerez, José M.& Franco, Leonardo. 2014. The Generalization Complexity Measure for Continuous Input Data. The Scientific World Journal،Vol. 2014, no. 2014, pp.1-9.
https://search.emarefa.net/detail/BIM-1051168
Modern Language Association (MLA)
Gómez, Iván…[et al.]. The Generalization Complexity Measure for Continuous Input Data. The Scientific World Journal No. 2014 (2014), pp.1-9.
https://search.emarefa.net/detail/BIM-1051168
American Medical Association (AMA)
Gómez, Iván& Cannas, Sergio A.& Osenda, Omar& Jerez, José M.& Franco, Leonardo. The Generalization Complexity Measure for Continuous Input Data. The Scientific World Journal. 2014. Vol. 2014, no. 2014, pp.1-9.
https://search.emarefa.net/detail/BIM-1051168
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1051168