Improving the Generalization Ability of MCE/GPD Learning and its Application to Multistage Building Learning
p. 298-316
Résumé
The Minimum Classification Error (MCE) / Generalized Probabilistic Descent (GPD) learning proposed by Katagiri and Juang in 1992 has attracted a great deal of attention for its high recognition performance and wide range of applications including the case where the length of feature vectors is variable like speech recognition. In this report, we propose a new method to improve the generalization performance of the MCE learning by employing an regularization technique which is widely used to solve ill-posed problems. Feed-forward neural networks are employed to evaluate the performance of the proposed method.
Index
Texte
Citer cet article
Référence papier
Jun Rokui, « Improving the Generalization Ability of MCE/GPD Learning and its Application to Multistage Building Learning », CASYS, 15 | 2004, 298-316.
Référence électronique
Jun Rokui, « Improving the Generalization Ability of MCE/GPD Learning and its Application to Multistage Building Learning », CASYS [En ligne], 15 | 2004, mis en ligne le 30 July 2024, consulté le 20 September 2024. URL : http://popups.lib.uliege.be/1373-5411/index.php?id=2178
Auteur
Jun Rokui
Department of the Interdisciplinary Faculty of Science and Engineering, Shimane University. 10600 Nishikawatsu-cho, Matsue-shi, 690-8504 Japan