Hodych O. Inductive methods and algorithms for self-organising data modeling based on Kohonen's maps

Українська версія

Thesis for the degree of Candidate of Sciences (CSc)

State registration number

0410U005672

Thesis Registration Form

0410U005672.pdf

Applicant for

Specialization

  • 01.05.03 - Математичне та програмне забезпечення обчислювальних машин і систем

29-09-2010

Specialized Academic Board

Д 35.052.05

Lviv Polytechnic National University

Essay

The goal of this thesis is to advance the state of inductive data modeling methods and algorithms based on Kohonen's self-organising maps (SOM) with an emphasis on exploratory data analysis, descriptive data models and data visualisation. A new training method "Neural Migration" for SOM and a new dynamic interval SOM are developed. Their application to the test datasets yields significant improvements over alternatives. The improved algorithm for data visualisation based on SOM and a derived from it image segmentation method are considered in the second part of the thesis.

Read more

Files

aref.doc

dys.pdf

Similar theses

0421U104038

Petrenko Maksym V.

Methods of integration of heterogeneous bibliographic data

0421U104040

Artabaev Yurii Z.

A technique for increasing the accuracy of integrated navigation systems based on predictive models using genetic algorithms.

0421U103593

Zubko Roman Anatoliyovych

Improving methods to increase the time efficiency of fractal image compression

0421U103401

Chystyakova Inna S.

Mapping method between the description logic and the relational data model.

0421U103320

Bielozorova Yana Andriivna

Method of application of wavelet analysis in problems of identification of speech information