2011 | OriginalPaper | Buchkapitel
Using Two-Step Modified Parallel SOM for Song Year Prediction
verfasst von : Petr Gajdoš, Pavel Moravec
Erschienen in: Digital Information Processing and Communications
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This paper uses a simple modification of classic Kohonen network (SOM), which allows parallel processing of input data vectors or partitioning the problem in case of insufficient memory for all vectors from the training set for computation of SOM by CUDA on YearPredictionMSD Data Set. The algorithm, presented in previous paper pre-selects potential centroids of data clusters and uses them as weight vectors in the final SOM network. The sutability of this algorithm has been already demonstrated on images as well as on two well-known datasets of hand-written digits.