XOR Artificial Neural Network
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60461373%3A22340%2F02%3A00007037" target="_blank" >RIV/60461373:22340/02:00007037 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
XOR Artificial Neural Network
Original language description
The basic element of data processing is a bipolar neuron with integer weights. This element of ANN enables to realize the exclusive or (XOR) function as a sub-network with one hidden layer. Then the heterogenous ANN is defined as an acyclic orientedgraphconsisting of two types of nodes: bipolar and XOR elements. The proverb "Exceptions prove the rule" is not only a phrase but a model of hypothesis refinement. The XOR artificial neural network is defined in the paper and its complexity is studied. The second possibility is to use XOR elements for systematic preprocessing. Both XOR preprocessing network and XOR model of exceptions are tested on difficult task of prime number recognition. The complexities of resulting heterogenous networks are compared with the complexities of conjunctive and disjunctive normal forms.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—
Result continuities
Project
—
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2002
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proc. of 8th Int. Conference on Soft Computing MENDEL 2002
ISBN
80-214-2135-5
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
221-226
Publisher name
VUT Brno
Place of publication
Brno
Event location
Brno
Event date
Jun 5, 2002
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—