Sitchov A. A research of improvement methods for neural associative memory and its application to hybrid neural networks

Українська версія

Thesis for the degree of Candidate of Sciences (CSc)

State registration number

0403U001716

Thesis Registration Form

0403U001716.pdf

Applicant for

Specialization

  • 01.05.03 - Математичне та програмне забезпечення обчислювальних машин і систем

21-05-2003

Specialized Academic Board

Д26.204.01

Essay

This dissertation is dedicated to improvement of neural associative memory, particularly using methods based on controlling net properties by synapse (weight) matrix deformation. The problem of hybrid modular neural networks creating is considered. It is proposed the ways of use of neural networks based on improved associative memory consisting of hybrid modular networks.

Read more

Files

ARefer.doc

Dis_1.doc

Dis_2.doc

Dis_3.doc

Dis_4.doc

Dis_4.doc

Dis_5.doc

Dis_6.doc

Dis_6.doc

Dis_7.doc

Dis_8.doc

Dis_9.doc

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