Tsymbal Y. Models and algorithms of multivariate data visualization on the basis of autoassociative neural networks

Українська версія

Thesis for the degree of Candidate of Sciences (CSc)

State registration number

0404U002783

Thesis Registration Form

0404U002783.pdf

Applicant for

Specialization

  • 05.13.23 - Системи та засоби штучного інтелекту

09-06-2004

Specialized Academic Board

Д 35.813.01

Essay

The thesis is devoted to creation of intelligent neural network system for multivariate data visualization, the development of program models of neural networks and methods of their learning and customization. The improved architecture of the autoassociative neural network with introduction of blocks of direct and inverse functional transformations and correction of output data is offered, the program neural network is created. The set of criteria for synthesis and estimation of operation quality for neural network with optimal complexity is developed.

Read more

Files

Liter.doc

aref.doc

dodatky.doc

rozd_1.doc

rozd_2.doc

rozd_3.doc

rozd_4.doc

rozd_5.doc

skoroch.doc

tytul.doc

vstup.doc

vys.doc

zmist.doc

Similar theses

0523U100039

Melnykova Natalya I.

Models and methods for supporting personalized solutions in medical systems.

0421U102573

Vlasenko Oleksandr Mykolayovych

Soft Computing methods and models of risk analysis processes intellectualization

0521U101170

Povkhan Ihor Fedorovych

Methods and principles of constructing discrete object classification trees for data mining.

0521U100926

Pavlyshenko Pavlyshenko Mykhaylovych

Methods of intellectual analysis of consolidated data for decision-making support

0421U101008

Mishchuk Oleksandra Sergijivna

Neural-like methods and tools to forecast the parameters of atmospheric air pollution