Neural Computing and Applications

, Volume 26, Issue 5, pp 1103–1115

SARASOM: a supervised architecture based on the recurrent associative SOM

  • David Gil
  • Jose Garcia-Rodriguez
  • Miguel Cazorla
  • Magnus Johnsson
Original Article


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.


Recurrent associative self-organizing map Supervised learning Prediction Sequence learning Elman network Recurrent neural network Hidden Markov model 

Copyright information

© The Natural Computing Applications Forum 2014

Authors and Affiliations

  • David Gil
    • 1
  • Jose Garcia-Rodriguez
    • 2
  • Miguel Cazorla
    • 3
  • Magnus Johnsson
    • 4
  1. 1.Lucentia Research Group, Computing Technology and Data ProcessingUniversity of AlicanteAlicanteSpain
  2. 2.Computing Technology and Data ProcessingUniversity of AlicanteAlicanteSpain
  3. 3.Instituto de Investigación en Informática (IUII)University of AlicanteAlicanteSpain
  4. 4.Lund University Cognitive ScienceLundSweden

Personalised recommendations