RESEARCH ARTICLE


Neural Networks Art: Solving Problems with Multiple Solutions and New Teaching Algorithm



Dmitrienko V. D*, Yu. Zakovorotnyi A, Yu. Leonov S, Khavina I. P
National Technical University "Kharkov Polytechnic Institute", Kharkov, Ukraine


Article Metrics

CrossRef Citations:
0
Total Statistics:

Full-Text HTML Views: 2366
Abstract HTML Views: 1438
PDF Downloads: 501
Total Views/Downloads: 4305
Unique Statistics:

Full-Text HTML Views: 1240
Abstract HTML Views: 904
PDF Downloads: 344
Total Views/Downloads: 2488



Creative Commons License
© Dmitrienko et al.; Licensee Bentham Open.

open-access license: This is an open access article licensed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/) which permits unrestricted, non-commercial use, distribution and reproduction in any medium, provided the work is properly cited.

* Address correspondence to this author at the National Technical University "Kharkov Polytechnic Institute", Kharkov, Ukraine; Tel: +380577076198; E-mail: valdmitrienko@gmail.com


Abstract

A new discrete neural networks adaptive resonance theory (ART), which allows solving problems with multiple solutions, is developed. New algorithms neural networks teaching ART to prevent degradation and reproduction classes at training noisy input data is developed. Proposed learning algorithms discrete ART networks, allowing obtaining different classification methods of input.

Keywords: Degradation of breeding classes, learning algorithms, neural network adaptive resonance theory, problems with multiple solutions..