Kotsovsky V. Learning of the generalized neuron-based artificial neural networks

Українська версія

Thesis for the degree of Candidate of Sciences (CSc)

State registration number

0413U005082

Thesis Registration Form

0413U005082.pdf

Applicant for

Specialization

  • 05.13.23 - Системи та засоби штучного інтелекту

12-06-2013

Specialized Academic Board

Д 35.052.14

Lviv Polytechnic National University

Essay

The thesis is devoted to the research of the properties of generalized neurons and artificial neural networks, the development of the learning methods, neural net simulation, the design of IT solutions for forecasting. The new properties of bithreshold neurons, polynomial neurons and complex weighted neurons with discrete activation functions are established. The new or mod-ified learning techniques are proposed also the learning algorithms behavior, convergence, computational speed and complexity are studied.

Read more

Files

Kots_disser.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