Please use this identifier to cite or link to this item: https://hdl.handle.net/10316/27727
Title: Eigenvalue decay: a new method for neural network regularization
Authors: Ludwig, Oswaldo 
Nunes, Urbano 
Araujo, Rui 
Keywords: Transduction; Regularization; Genetic algorithm; Classification margin; Neural network
Issue Date: 26-Jan-2014
Publisher: Elsevier
Citation: LUDWIG, Oswaldo; NUNES, Urbano; ARAUJO, Rui - Eigenvalue decay: a new method for neural network regularization. "Neurocomputing". ISSN 0925-2312. Vol. 124 (2014) p. 33–42
Serial title, monograph or event: Neurocomputing
Volume: 124
Abstract: This paper proposes two new training algorithms for multilayer perceptrons based on evolutionary computation, regularization, and transduction. Regularization is a commonly used technique for preventing the learning algorithm from overfitting the training data. In this context, this work introduces and analyzes a novel regularization scheme for neural networks (NNs) named eigenvalue decay, which aims at improving the classification margin. The introduction of eigenvalue decay led to the development of a new training method based on the same principles of SVM, and so named Support Vector NN (SVNN). Finally, by analogy with the transductive SVM (TSVM), it is proposed a transductive NN (TNN), by exploiting SVNN in order to address transductive learning. The effectiveness of the proposed algorithms is evaluated on seven benchmark datasets.
URI: https://hdl.handle.net/10316/27727
ISSN: 0925-2312
DOI: 10.1016/j.neucom.2013.08.005
Rights: openAccess
Appears in Collections:I&D ISR - Artigos em Revistas Internacionais

Files in This Item:
File Description SizeFormat
Eigenvalue decay.pdf718.75 kBAdobe PDFView/Open
Show full item record

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.