File Entry: LoopSOM: A Robust SOM Variant Using Self-Organizing Temporal Feedback Connections

Paper accepted in the VIII ENIA - Encontro Nacional de Inteligência Artificial. To appear in proceedings of the XXIX CSBC - Congresso da Sociedade Brasileira de Computação.

Abstract. This paper introduces feedback connections into a previously proposed model of the simple and complex neurons of the neocortex. The original model considers only feedforward connections between a SOM (Self-Organizing Map) and a RSOM (Recurrent SOM). A variant of the SOM-RSOM pair is proposed,
called LoopSOM. The RSOM sends predictions to the SOM, providing more robust pattern classification/recognition and solving ambiguities.