SARASOM: a supervised architecture based on the recurrent associative SOM
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/57815
Título: | SARASOM: a supervised architecture based on the recurrent associative SOM |
---|---|
Autor/es: | Gil, David | Garcia-Rodriguez, Jose | Cazorla, Miguel | Johnsson, Magnus |
Grupo/s de investigación o GITE: | Lucentia | Informática Industrial y Redes de Computadores | Robótica y Visión Tridimensional (RoViT) |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Tecnología Informática y Computación | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial | Universidad de Alicante. Instituto Universitario de Investigación Informática |
Palabras clave: | Recurrent associative self-organizing map | Supervised learning | Prediction | Sequence learning | Elman network | Recurrent neural network | Hidden Markov model |
Área/s de conocimiento: | Arquitectura y Tecnología de Computadores | Ciencia de la Computación e Inteligencia Artificial |
Fecha de publicación: | jul-2015 |
Editor: | Springer London |
Cita bibliográfica: | Neural Computing and Applications. 2015, 26(5): 1103-1115. doi:10.1007/s00521-014-1785-8 |
Resumen: | We present and evaluate a novel supervised recurrent neural network architecture, the SARASOM, based on the associative self-organizing map. The performance of the SARASOM is evaluated and compared with the Elman network as well as with a hidden Markov model (HMM) in a number of prediction tasks using sequences of letters, including some experiments with a reduced lexicon of 15 words. The results were very encouraging with the SARASOM learning better and performing with better accuracy than both the Elman network and the HMM. |
Patrocinador/es: | We want to express our acknowledgment to the Ministry of Science and Innovation (Ministerio de Ciencia e Innovación—MICINN) through the “José Castillejo” program from the Government of Spain and to the Swedish Research Council through the Swedish Linnaeus project Cognition, Communication and Learning (CCL) as funders of the work exhibited in this paper. This work was also partially funded by the Spanish Government DPI2013- 40534-R. |
URI: | http://hdl.handle.net/10045/57815 |
ISSN: | 0941-0643 (Print) | 1433-3058 (Online) |
DOI: | 10.1007/s00521-014-1785-8 |
Idioma: | eng |
Tipo: | info:eu-repo/semantics/article |
Derechos: | © The Natural Computing Applications Forum 2014. The final publication is available at Springer via http://dx.doi.org/10.1007/s00521-014-1785-8 |
Revisión científica: | si |
Versión del editor: | http://dx.doi.org/10.1007/s00521-014-1785-8 |
Aparece en las colecciones: | INV - LUCENTIA - Artículos de Revistas INV - I2RC - Artículos de Revistas INV - RoViT - Artículos de Revistas INV - AIA - Artículos de Revistas |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
2015_Gil_etal_NeuralComput&Applic_final.pdf | Versión final (acceso restringido) | 1,62 MB | Adobe PDF | Abrir Solicitar una copia |
Todos los documentos en RUA están protegidos por derechos de autor. Algunos derechos reservados.