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 | Size | Format | |
---|---|---|---|---|
Eigenvalue decay.pdf | 718.75 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.