A new convex objective function for the supervised learning of single-layer neural networks
Authors:
- Oscar Fontenla-RomeroOFOscar Fontenla-Romero
- Bertha Guijarro-BerdiñasBGBertha Guijarro-Berdiñas
- Beatriz Pérez-SánchezBPBeatriz Pérez-Sánchez
- Amparo Alonso-BetanzosAAAmparo Alonso-Betanzos
- 1 May 2010
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 43 (5) , 1984-1992
Abstract
No abstract availableFunding Information
- Ministerio de Educación, Cultura y Deporte (TIN2006-02402)
- European Regional Development Fund
- Xunta de Galicia (08TIC012105PR)
This publication has 16 references indexed in Scilit:
- An improved algorithm for learning long-term dependency problems in adaptive processing of data structuresIEEE Transactions on Neural Networks, 2003
- A new method in determining initial weights of feedforward neural networks for training enhancementNeurocomputing, 1997
- On the uniqueness of weights in single-layer perceptronsIEEE Transactions on Neural Networks, 1996
- On a natural homotopy between linear and nonlinear single-layer networksIEEE Transactions on Neural Networks, 1996
- Exploring and comparing the best "direct methods" for the efficient training of MLP-networksIEEE Transactions on Neural Networks, 1996
- A learning algorithm for multilayered neural networks based on linear least squares problemsNeural Networks, 1993
- A fast new algorithm for training feedforward neural networksIEEE Transactions on Signal Processing, 1992
- 30 years of adaptive neural networks: perceptron, Madaline, and backpropagationProceedings of the IEEE, 1990
- Back propagation fails to separate where perceptrons succeedIEEE Transactions on Circuits and Systems, 1989
- Fast recursive algorithms for a class of linear equationsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1982