Selecting coefficients for image processing using non-supervised neural nets

Title:

Selecting coefficients for image processing using non-supervised neural nets

Creator:

Isasi, Pedro, Velasco, Manuel, and Segovia, Javier

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:801966d8-f682-4ab3-8076-1ec4a79669be
uuid:801966d8-f682-4ab3-8076-1ec4a79669be

Subject:

non-supervised neural nets, sensitivity analysis, image classification, and face recognition

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

This paper introduces a new sensitivity analysis method using nonsupervised neural nets, based on the Adaptive Resonance Theory (ART).This new method introduces the possibility of a sensitivity analysis being adaptive and being conducted at the saine tirne as net learning is taking place, taking advantage of the property of continuous (as opposed to phase-wise) learning of ART models. A sensitivity analysis can be conducted likewise, i.e. continuous by and capably adapting to any new relationships appearing among the input data. The method has been validated in the field of feature detection for iniage classification and, more specifically, for face recognition.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Neural network world: international journal on neural and mass-parallel computing and information systems | 2002 Volume:12 | Number:1

Harvested from:

CDK

Metadata only:

false