Fast calculation of correlations in recognition systems

03/06/2016

∙

by   Pavel Dourbal, et al.

∙

0

∙

share

Computationally efficient classification system architecture is proposed. It utilizes fast tensor-vector multiplication algorithm to apply linear operators upon input signals . The approach is applicable to wide variety of recognition system architectures ranging from single stage matched filter bank classifiers to complex neural networks with unlimited number of hidden layers.