ALGORITHM OF NEURON NETWORKS MODIFICATION
Journal Title: Електроніка та системи управління - Year 2018, Vol 2, Issue 56
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
- EP ID EP522932
- DOI 10.18372/1990-5548.56.12936
- Views 130
- Downloads 0
SAFETY ENHANCEMENT ALGORITHMS OF THE MICRO-UAV PILOTING
The article is devoted to algorithms development of piloting with enhanced safety for micro-UAV. The critical situations arising during the flight, typical failure of the electrical equipment of the ground station commun...
CONCEPTUAL DESIGN OF SOLAR UNMANNED AERIAL VEHICLE
In this paper, emphasis was placed on the fact that a solar unmanned aerial vehicle, should be used in the context of certain missions, taking into account this, the general structure of the aircraft's internal systems w...
WIRELESS SOLAR POWER PLANT MONITORING SYSTEM
Monitoring systems are the most important part of modern solar power stations. Article contains the description of the existing monitoring systems, and their shortcomings are given. It is shown that as an alternative way...
NEURON MODEL SIGMOID ACTIVATION FUNCTION BASED ON MULTI-OPTIONAL FUNCTIONS ENTROPY CONDITIONAL OPTIMIZATION DOCTRINE
It is made an attempt to discover an explainable plausible reason for a neuron activation function, of a sigmoid type function like logistic function, substantiation in terms of the multi-optional conditional optimality...
USING THE THEORY OF MARTINGALES TO PROVE THE SOUNDNESS OF THE ESTIMATES OF THE PARAMETERS OF LINEAR DYNAMIC SYSTEMS
The article is devoted to analytical methods of research of filtration algorithms in conditions of a priori uncertainty of information on statistical characteristics of state noise and measurement in linear dynamic syste...