Optical Memory and Neural Networks

, Volume 22, Issue 3, pp 184–192

Pattern recognition and increasing of the computational efficiency of a parallel realization of the probabilistic neural network with homogeneity testing

Article

DOI: 10.3103/S1060992X13030090

Cite this article as:
Savchenko, A.V. Opt. Mem. Neural Networks (2013) 22: 184. doi:10.3103/S1060992X13030090

Abstract

The research subject is the computational complexity of the probabilistic neural network (PNN) in the pattern recognition problem for large model databases. We examined the following methods of increasing the efficiency of a neural-network classifier: a parallel multithread realization, reducing the PNN to a criterion with testing of homogeneity of feature histograms of input and reference images, approximate nearest-neighbor analyses (Best-Bin First, directed enumeration methods). The approach was tested in facial-recognition experiments with FERET dataset.

Keywords

pattern recognition probabilistic neural network test of homogeneity directed enumeration method parallel multithread computations 

Copyright information

© Allerton Press, Inc. 2013

Authors and Affiliations

  1. 1.Business Informatics and Applied Mathematics DepartmentNational Research University Higher School of EconomicsNizhny NovgorodRussia

Personalised recommendations