Artificial neural networks in problems of material objects implementation. Part 2. Design and application specifics

Abstract

In this work paradigms and rules of neural networks learning are considered in a generalized form and the relationship between them are analyzed. The major tasks which can be solved by means of neural networks are analyzed. The main problem of using neural networks in problems of material objects implementation are defined in need of further theoretical research. The expediency of usage neural networks ensembles are substantiated with the followed by their transformation under specific applied design problems.

Authors and Affiliations

V. Adamenko, G. Mirskikh

Keywords

Related Articles

Artificial neural networks in problems of material objects implementation. Part 1. Networking principles and Classification

The main historical development stages of artificial neural networks are presented. The mathematical model of artificial neurons and the basic elements of neural networks are considered. Typical activation functions are...

Optimal spatial processing effectiveness indexes calculation for fixed wireless communication system radiolink.

Introduction. The effectiveness of the theoretical results of optimal spatial processing ot-wo radio signals at the receiving side of wireless communication system with two radio signals which operating simultaneously on...

Modeling of microstrip analogue of a photon crystal

The comparative modeling of microstrip analogue of a photon crystal by an impedance method, diner’s method and method of final integrals is considered. The characteristics which show mutual conformity of results are give...

Suppression of bulk waves in surface acoustic wave filter

Introduction. One of the dominant second order effects in devices based on surface acoustic waves (SAW) is the excitation of parasitic bulk acoustic waves (BAW). Attention is drawn to the lack of effectiveness of traditi...

Determination of homogeneity zone of controlled quasistatic electric field in the area with the ring multiply boundary

The analysis and calculation of zone homogeneity of controlled (rotated) quasi-static electric field in the interior of the open area with circular multiply connected boundary and of equal length, depending on connectivi...

Download PDF file
  • EP ID EP309289
  • DOI 10.20535/RADAP.2012.48.213-221
  • Views 57
  • Downloads 0

How To Cite

V. Adamenko, G. Mirskikh (2012). Artificial neural networks in problems of material objects implementation. Part 2. Design and application specifics. Вісник НТУУ КПІ. Серія Радіотехніка, Радіоапаратобудування, 0(48), 213-221. https://europub.co.uk./articles/-A-309289