Haimoudi E. Models and methods of recognition of classes of multivariate objects on the basis of artificial neural networks

Українська версія

Thesis for the degree of Candidate of Sciences (CSc)

State registration number

0404U002653

Thesis Registration Form

0404U002653.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 development of architecture and theories of operation of an intellectual system of pattern recognition on the basis of artificial neural networks (ANN) with competitive learning. The method of ANN data preprocessing which provides the extension of dimensionality of realization space on the basis of geometric approach has been offered. For visualization of recognition results the model of a three-dimensional map of features has been offered.

Read more

Files

DYS-Liter.doc

DYS-Tytul.doc

DYS-dadatk.doc

DYS-list-dodatk.doc

DYS-rozd_1.doc

DYS-rozd_2.doc

DYS-rozd_3.doc

DYS-rozd_4.doc

DYS-vstyp.doc

DYS-zmist.doc

aref.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