paper

Fast calculation of correlations in recognition systems

arXiv:1603.01772

Abstract

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.

7 pages

Fast calculation of correlations in recognition systems · wovepaper