Otavio A.S. Carpinteiro, Harry G. Barrow
A novel neural model made up of two self-organizing map nets - one on top of the other - is introduced and analysed experimentally. The model makes an effective use of context information, and that enables it to perform sequence classification and discrimination efficiently. It was successfully applied to a set of contrived sequences, and also to a real sequence - the third voice of the sixteenth four-part fugue in G minor of the Well-Tempered Clavier (vol. I) of J.S. Bach. The model has application in cognitive domains which demand classifying either a set of sequences of vectors in time or sub-sequences into a unique and large sequence of vectors in time.
Download compressed postscript file