Inductive Modelling of Temporal Sequences by Means of Self-organization

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F07%3A03132260" target="_blank" >RIV/68407700:21230/07:03132260 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Inductive Modelling of Temporal Sequences by Means of Self-organization
Original language description
In this paper we present a new self-organizing neural network, which builds a spatio-temporal model of an input temporal sequence inductively. The network is an extension of Kohonen's Self-organizing Map with a modified Hebb's rule for update of temporalsynapses. The model building behavior is shown on inductive learning of a transition matrix from a data generated by a Markov Chain.
Czech name
Inductive Modelling of Temporal Sequences by Means of Self-organization
Czech description
In this paper we present a new self-organizing neural network, which builds a spatio-temporal model of an input temporal sequence inductively. The network is an extension of Kohonen's Self-organizing Map with a modified Hebb's rule for update of temporalsynapses. The model building behavior is shown on inductive learning of a transition matrix from a data generated by a Markov Chain.

Publication year
2007
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceeding of International Workshop on Inductive Modelling
ISBN
978-80-01-03881-9
ISSN
—
e-ISSN
—
Number of pages
9
Pages from-to
269-277
Publisher name
Czech Technical University
Place of publication
Prague
Event location
Praha
Event date
Sep 23, 2007
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)