Artificial Neuron with Homeostatic Behaviour

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21260%2F10%3A00174740" target="_blank" >RIV/68407700:21260/10:00174740 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Artificial Neuron with Homeostatic Behaviour
Original language description
Homeostasis is a property of a system that regulates its internal environment in order to maintain stable conditions. It is typical for any for biological systems and therefore also for neural cell. This paper presents a way how to use the idea of homeostasis in the field of artificial neural networks. The artificial neuron is here considered as an information homeostat. The state of equilibrium means a situation when the level of computational utility reaches its maximum. This idea is based on the presumption that the neuron has two inputs: first, the output of the neurons in the previous layer through its dendrites, and secondly the part of its output signal that is returned from the folowing layer through its axon. The presented idea is inspired bythe fact that the biological neuron can know which part of its output energy is accepted by other neurons. Several methods of the learning are presented.
Czech name
—
Czech description
—

Publication year
2010
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
The 2010 European Simulation and modelling conference
ISBN
978-90-77381-57-1
ISSN
—
e-ISSN
—
Number of pages
3
Pages from-to
—
Publisher name
EUROSIS - ETI
Place of publication
Ghent
Event location
Hasselt
Event date
Oct 25, 2010
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)