caa a22 4500 606160124 CHVBK 20210128100628.0 cr unu---uuuuu 210128e20150701xx s 000 0 eng 10.1007/s00521-014-1785-8 doi (NATIONALLICENCE)springer-10.1007/s00521-014-1785-8 SARASOM: a supervised architecture based on the recurrent associative SOM [Elektronische Daten] [David Gil, Jose Garcia-Rodriguez, Miguel Cazorla, Magnus Johnsson] 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. The Natural Computing Applications Forum, 2014 Recurrent associative self-organizing map nationallicence Supervised learning nationallicence Prediction nationallicence Sequence learning nationallicence Elman network nationallicence Recurrent neural network nationallicence Hidden Markov model nationallicence Gil David Lucentia Research Group, Computing Technology and Data Processing, University of Alicante, Alicante, Spain aut Garcia-Rodriguez Jose Computing Technology and Data Processing, University of Alicante, Alicante, Spain aut Cazorla Miguel Instituto de Investigación en Informática (IUII), University of Alicante, Alicante, Spain aut Johnsson Magnus Lund University Cognitive Science, Lund, Sweden aut Neural Computing and Applications Springer London 26/5(2015-07-01), 1103-1115 0941-0643 26:5<1103 2015 26 521 https://doi.org/10.1007/s00521-014-1785-8 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00521-014-1785-8 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Gil David Lucentia Research Group, Computing Technology and Data Processing, University of Alicante, Alicante, Spain aut NATIONALLICENCE 700 1- Garcia-Rodriguez Jose Computing Technology and Data Processing, University of Alicante, Alicante, Spain aut NATIONALLICENCE 700 1- Cazorla Miguel Instituto de Investigación en Informática (IUII), University of Alicante, Alicante, Spain aut NATIONALLICENCE 700 1- Johnsson Magnus Lund University Cognitive Science, Lund, Sweden aut NATIONALLICENCE 773 0- Neural Computing and Applications Springer London 26/5(2015-07-01), 1103-1115 0941-0643 26:5<1103 2015 26 521