Temporal Mapping in Categorizing and Learning Module

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F04%3A03101067" target="_blank" >RIV/68407700:21230/04:03101067 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Temporal Mapping in Categorizing and Learning Module

Original language description

This paper describes modifications of an existing neural network called Categorizing and Learning Module (CALM) that allow learning of temporal sequences. We embedded an associative learning mechanism which allows to look into the past when classifying present stimuli. Our modification uses the Euclidean metrics instead of the original weighted sum. The enhanced module was tested on simple artificial data. The experiments promise applicability in a real problem domain.

Czech name

Není k dispozici

Czech description

Není k dispozici

Type

A - Audiovisual production

CEP classification

IN - Informatics

OECD FORD branch

—

Project

—

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2004

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

ISBN

—

Place of publication

Praha

Publisher/client name

—

Version

—

Carrier ID

neuvedeno