NEURAL NETWORKS MODULE

Abstract

It is considered a basic approach for hybrid neuron network creation. As an example, the counter propagation neural network is analyzed. It is effectively used for image processing. Two modes of this neuron network functioning are considered. They are: accreditation and interpolation. Interpolation mode permits to reveal more complex features and can supply more precise results. Based on this analysis it is developed a new hybrid structure that includes Kohonnen neural network and perceptron. It is proposed a learning algorithm of this hybrid neuron network.

Authors and Affiliations

Olena Chumachenko, Ananatoliy Kot

Keywords

Related Articles

VERTICAL AXIS WIND TURBINE WITH ADJUSTABLE BLADES

It is researched the problem of energetic efficiency increasing of wind energy plant with vertical axis of rotation. For the solution of this problem it is proposed to use the adjustable blades. It is determined the o...

TEST BENCH OF AXIAL GENERATORS OF WIND POWER PLANTS

This article is devoted to the construction of a test bench for quality control of an axial generator, which is a part of a low-power wind power plant. The axial generator reaches the working power at a wind speed of 3–3...

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...

MODELING THE INFLUENCE OF FACTORS ON THE MONITORING OF THE LIGHT-SIGNAL FIRES OF THE CIVIL AVIATION AERODROME IN MATLAB ENVIRONMENT

The use of the created toolkit using the Matlab interface for determining the influence of factors on the monitoring of light-signal fires of the civil aviation aerodrome is proposed. The tools are used for defining visu...

ERRORS ESTIMATION OF EXTERNAL DISTURBANCE INFLUENCES

The main specific points of existing air navigation schemes with relation to external disturbing influences are discussed. Some new approach to analyze in the view of admissible temporal and spatial frames basic principl...

Download PDF file
  • EP ID EP522967
  • DOI 10.18372/1990-5548.56.12937
  • Views 133
  • Downloads 0

How To Cite

Olena Chumachenko, Ananatoliy Kot (2018). NEURAL NETWORKS MODULE. Електроніка та системи управління, 2(56), 64-68. https://europub.co.uk/articles/-A-522967