Features of the auto-associative neurolike structures of the geometrical transformation machine (GTM)

Author

Polishchuk, Uliana ; Tkachenko, Pavlo ; Tkachenko, Roman ; Yurchak, Irina

Author_Institution

Lviv Polytech. Nat. Univ., Lviv

fYear

2009

fDate

22-24 April 2009

Firstpage

66

Lastpage

67

Abstract

GTM neurolike structures provide solutions of such tasks as: pattern recognition, prediction tasks, classification, Principal Components Analysis, factor analysis, optimization, lost data renewal or its (data) compression, realization of information security methods, solution of algebraic equations systems (including underdetermined and overdetermined), high dimensional data visualization, etc.

Keywords

neural nets; optimisation; pattern classification; principal component analysis; GTM neurolike structures; algebraic equations systems; auto-associative neurolike structures; classification; data compression; factor analysis; geometrical transformation machine; information security methods; lost data renewal; optimization; pattern recognition; prediction tasks; principal components analysis; Data analysis; Electronic mail; Information analysis; Information security; Multilayer perceptrons; Neural networks; Optimization methods; Pattern analysis; Pattern recognition; Principal component analysis; Auto-associative neural network; Geometrical Transformation Machine; Multilayer perceptrons; Non-iterative training paradigm; Principal Components Analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Perspective Technologies and Methods in MEMS Design, 2009. MEMSTECH 2009. 2009 5th International Conference on

Conference_Location

Zakarpattya

Print_ISBN

978-966-2191-06-6

Type

conf

Filename

5069708