Self-Organizing Neural Networks for Signal Recognition
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F06%3A03121571" target="_blank" >RIV/68407700:21230/06:03121571 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Self-Organizing Neural Networks for Signal Recognition
Original language description
In this paper we introduce a self-organizing neural network that is capable of recognition of temporal signals. Conventional self-organizing neural networks like recurrent variant of Self-Organizing Map provide clustering of input sequences in space andtime but the identification of the sequence itself requires supervised recognition process, when such network is used. In our network called TICALM the recognition is expressed by speed of convergence of the network while processing either learned or anunknown signal. TICALM network capabilities are shown on an experiment with handwriting recognition.
Czech name
Není k dispozici
Czech description
Není k dispozici
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
—
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2006
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
16th International Conference, Athens, Greece, September 10-14, 2006. Proceedings, Part I
ISBN
3-540-38625-4
ISSN
—
e-ISSN
—
Number of pages
9
Pages from-to
406-414
Publisher name
Springer
Place of publication
Heidelberg
Event location
Athens
Event date
Sep 10, 2006
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—