dc.creator | Nova, David | |
dc.creator | Estévez Valencia, Pablo | |
dc.date.accessioned | 2019-05-29T13:41:02Z | |
dc.date.available | 2019-05-29T13:41:02Z | |
dc.date.created | 2019-05-29T13:41:02Z | |
dc.date.issued | 2017 | |
dc.identifier | 10.1109/WSOM.2017.8020029 | |
dc.identifier | https://repositorio.uchile.cl/handle/2250/169073 | |
dc.description.abstract | In this contribution we propose a new regularization method for the Generalized Matrix Learning Vector Quantization classifier. In particular we use a nuclear norm in order to prevent oversimplifying/over-fitting and oscillatory behaviour of the small eigenvalues of the positive semi-definite relevance matrix. The proposed method is compared with two other regularization methods in two artificial data sets and a real-life problem. The results show that the proposed regularization method enhances the generalization ability of GMLVQ. This is reflected in a lower classification error and a better interpretability of the relevance matrix. | |
dc.language | en | |
dc.publisher | IEEE | |
dc.rights | http://creativecommons.org/licenses/by-nc-nd/3.0/cl/ | |
dc.rights | Attribution-NonCommercial-NoDerivs 3.0 Chile | |
dc.source | 12th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization, WSOM 2017 - Proceedings | |
dc.subject | Artificial Intelligence | |
dc.subject | Computational Theory and Mathematics | |
dc.title | Spectral regularization in generalized matrix learning vector quantization | |
dc.type | Artículo de revista | |