Project ORGANIC: ORGANIC: Self-organized recurrent neural learing for language processing

2009-04-01 – 2012-03-31

Abstract

ORGANICE adopts principles of cortical architectures and self-organizing neurodynamics for the design of a new type of cognitive architectures. The principle inovations are deep multilevel learning based on recurrent networks using purely dynamic representations and trained both supervised and unsupervised. These techniques will be applied to large vocabulary speech recognition in noisy environments, end on handwriting recognition.