Homeostatic artificial neural network for models of human operator

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F16%3A00304567" target="_blank" >RIV/68407700:21730/16:00304567 - isvavai.cz</a>

Result on the web

<a href="http://www.impb.ru/icmbb/docs/ICMBB16.pdf" target="_blank" >http://www.impb.ru/icmbb/docs/ICMBB16.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Homeostatic artificial neural network for models of human operator

Original language description

Novel method for models of human brain processes with the use artificial neural networks is presented. The proposed learning algorithm of the neural network is able to find the optimal setting in a way that is similar to biological neuron. On the other hand, the algorithm is still enough simple to be calculated on standard hardware. The proposed network was tested on both artificial and real data. The main benefit is that the learning can continue even after the environment (the input and output matrix) changed. The results suggest that this type of learning can be useful also in other tasks of artificial learning and recognition.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

IN - Informatics

OECD FORD branch

—

Project

—

Continuities

V - Vyzkumna aktivita podporovana z jinych verejnych zdroju

Publication year

2016

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

МАТЕМАТИЧЕСКАЯ БИОЛОГИЯ И БИОИНФОРМАТИКА

ISBN

978-5-317-05377-2

ISSN

—

e-ISSN

—

Number of pages

4

Pages from-to

151-154

Publisher name

Institute of Mathematical Problems of Biology, RAS

Place of publication

Puschino

Event location

Puschino

Event date

Oct 16, 2016

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—