ALGORITHM OF NEURON NETWORKS MODIFICATION

Abstract

It is considered a problem of neuron network modification whose topology has been chosen previously as a result of optimization problem solution for given task. The proposed modification algorithm is based on two-stages procedure which consists of genetic algorithm and local algorithm of optimization. The problem of modification is represented as two tasks: the search of optimal neuron network structure and weight coefficients adjustment. For the solution of these two problems it is used two-stages algorithm, in which at the first stage it is applied hybrid multicriteria evolutionary algorithm and at the second stage it is determined values of weight coefficients with help of back propagation error method and method of steepest descent. The determination of optimal values of hidden layers quantity is executed with help of adaptive algorithm of merging and growing.

Authors and Affiliations

Olena Chumachenko

Keywords

Related Articles

MULTICRITERIA OPTIMIZATION PROBLEM STATEMENT IN ELECTRIC POWER INDUSTRY

In this paper, optimization problems of the electric power industry, modeled on the basis of nonstationary nonlinear systems, are considered. The analysis of admissible solutions of the optimization problem is performed...

INTELECTUAL APPROACH TO THE DESIGN OF WIND ENERGY PLANT ROTOR PARAMETERS

It is considered a wind power plant rotor design problem for a rotor with vertical axis of rotation. It is proposed an approarch of efficiency improvement by combined rotor design, consisting of some basic rotors (Darrie...

INVERTER OF THE AUTOMATED SYSTEM FOR DETERMINING THE CHARACTERISTICS OF SEMICONDUCTOR DEVICES

This article is devoted to the issues of building the inverter for automated determination system of semiconductor devices volt-ampere characteristics. In the article the structure of such a system is considered and it i...

ACCURACY RESEARCH METHOD OF THE MODIFIED ALGORITHM FOR DETECTING LINEAR LANDMARKS

A search algorithm for the most extended landmark by which unmanned aerial vehicle can be followed by and implemented flight correction was proposed. The software was developed based on the Python language. The functiona...

INFORMATION SYSTEM FOR THE EXAMINATION OF ORGANISM ADAPTATION CHARACTERISTICS OF FLIGHT CREWS’ PERSONNEL

Аn information system is proposed for the examination of flight crew members’ functional states; the system is based on the concept of human's organism’s oxygen regimes control. It was implemented on the base of the data...

Download PDF file
  • EP ID EP522932
  • DOI 10.18372/1990-5548.56.12936
  • Views 136
  • Downloads 0

How To Cite

Olena Chumachenko (2018). ALGORITHM OF NEURON NETWORKS MODIFICATION. Електроніка та системи управління, 2(56), 59-63. https://europub.co.uk/articles/-A-522932