Classification of Spatio-Temporal Data Using Complex-Valued Neural Networks

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F11%3A00184208" target="_blank" >RIV/68407700:21240/11:00184208 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Classification of Spatio-Temporal Data Using Complex-Valued Neural Networks
Original language description
This paper presents a new approach in spatio-temporal classification utilizing the fact, that spatio-temporal data can be easily transformed into polar form of complex numbers. The proposed classifier uses two-layer complex-valued neural network inspiredby the RBF networks. Weights of the first layer determine spatio-temporal position of neurons and are trained using neural gas algorithm to appropriately cover the training data set. The second layer divides neurons from the first layer into different classes and is trained in single pass. The classification itself is based on accumulating distance error from neural network. Paper contains details on experimenting with proposed approach on artificial data of hand-written character recognition.
Czech name
—
Czech description
—

Project
—
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)<br>S - Specificky vyzkum na vysokych skolach

Publication year
2011
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceeding of the 7th Doctoral Workshop on Mathematical and Engineering Methods in Computer Science
ISBN
978-80-214-4305-1
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
94-101
Publisher name
Brno University of Technology
Place of publication
Brno
Event location
Lednice
Event date
Oct 14, 2011
Type of event by nationality
CST - Celostátní akce
UT code for WoS article
—

Similar results(10)