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: 430
Abstract HTML Views: 229
PDF Downloads: 81
Total Views/Downloads: 740
Unique Statistics:

Full-Text HTML Views: 269
Abstract HTML Views: 148
PDF Downloads: 70
Total Views/Downloads: 487



© 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..