SARASOM: a supervised architecture based on the recurrent associative SOM

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.

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.