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

ALGORITHM OF OPTIMAL CONTROL OF UAV GROUP

The article proposes the algorithm of optimal control of unmanned aerial vehicle group allowing to set maneuvers of unmanned aerial vehicles, to estimate the coordinates of current position of unmanned aerial vehicle rel...

COMPRESSION ALGORITHM OF VOICE CONTROL COMMANDS OF UAV BASED ON WAVELET TRANSFORM

It is proposed to use developed digital speech signal compression algorithm based on wavelet transform in the unmanned aerial vehicle voice control system. It is implemented the estimation of compression data ratio and b...

STRUCTURAL SYNTHESIS OF HYBRID NEURAL NETWORKS ENSEMBLES

It is considered the structural synthesis of hybrid neural networks ensembles. It is chosen the ensemble topology as parallel structure with united layer. It is developed a hybrid algorithm for the problem solution which...

ALGORITHM OF VARIATIVE FEATURE DETECTION AND PREDICTION IN CONTEXT-DEPENDENT RECOGNITION

Application of context-dependent classification for recognition tasks is proposed. In the context-free classification, the starting point was the Bayesian classifier. Morphological features such as object form, area, and...

MAGNETORESISTIVE TRANSFORMER ON THIN FILMS

The statistical processing of the results for a three-time measurement of active power by a magnetoresistive converter is given. In the statistical processing of the threefold result of measuring the active power by a ma...

Download PDF file
  • EP ID EP514464
  • DOI 10.18372/1990-5548.58.13508
  • Views 158
  • 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