STRUCTURAL-PARAMETRIC SYNTHESIS OF THE FEEDFORWARD NEURAL NETWORKS WITH SIGMOID PIECEWISE-TYPE NEURONS

Abstract

The method of structural and parametric synthesis of feedforward neural networks is considered, which includes Sigmoid Piecewise neurons, used in the process of a predictive model construction. The article describes the principles of a new developed Sigmoid Piecewise neuron constructing. It is proposed the method of structural and parametric synthesis with a single layer of Sigmoid Piecewise neurons.The training algorithm of proposed neural networks is developed. The results of the effectiveness research of Sigmoid Piecewise neurons on real samples are presented.

Authors and Affiliations

Michael Zgurovsky, Olena Chumachenko, Vladyslav Gorbatiuk

Keywords

Related Articles

THE METHOD OF DYNAMIC DESIGN OF A SEARCH ENGINE BASED ON AUTOMATED ANALYSIS OF USER REQUESTS

The article describes the method of dynamically designing a search engine based on the analysis of user search queries and automated user's document generation. The advanced method of dynamic search with the account of i...

LOCAL POLARIMETRIC SYSTEM FOR MEASURING AIRCRAFT`S NAVIGATION AND PILOTING PARAMETERS

The paper considers questions of invention the local optical system for measuring navigation and piloting parameters on base on polarimetric technologies. Such system is aimed to increase the sensitivity and accuracy of...

SUGGESTIONS TO THE METHODS FOR ASSESSING THE QUALITY OF THE GLIDE PATH ENTRANCE

The article deals with issues related to the assessment of the aircraft piloting quality. Also, the factors affecting the technique of piloting crews in emergency situations in flight were analyzed. As the result, the sp...

INVESTIGATION OF BLADE ATTACK ANGLE VALUE ON VERTICAL AXIAL WIND POWER PLANT

In this paper, the efficiency of the vertical-axial wind power plant at various wind speeds depending on the angle of attack of the rotor blades was investigated. The object of the investigation was a three-bladed Darr...

ALGORITHM OF NEURON NETWORKS MODIFICATION

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...

Download PDF file
  • EP ID EP514464
  • DOI 10.18372/1990-5548.58.13508
  • Views 168
  • Downloads 0

How To Cite

Michael Zgurovsky, Olena Chumachenko, Vladyslav Gorbatiuk (2018). STRUCTURAL-PARAMETRIC SYNTHESIS OF THE FEEDFORWARD NEURAL NETWORKS WITH SIGMOID PIECEWISE-TYPE NEURONS. Електроніка та системи управління, 4(58), 42-47. https://europub.co.uk/articles/-A-514464