Towards Basic Level Categories in Cognitive Agents

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F17%3A50014629" target="_blank" >RIV/62690094:18450/17:50014629 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1109/FSKD.2017.8393302" target="_blank" >http://dx.doi.org/10.1109/FSKD.2017.8393302</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/FSKD.2017.8393302" target="_blank" >10.1109/FSKD.2017.8393302</a>

Result language

angličtina

Original language name

Towards Basic Level Categories in Cognitive Agents

Original language description

Cognitive agents seem to be a perfect fit to computational solutions capable of making sense of large datasets and facilitating interaction with human users. Following cognitive computing paradigm we present an approach towards modelling category-based organisation of agent&apos;s semantic memory. As such, we investigate the process of formation and utilization of basic level categories in autonomous systems. We provide a detailed description of internal organisation of agent&apos;s semantic memory inspired by results from cognitive science. In particular, we focus on providing a concise description of a preliminary computational model (proof of concept&apos;s implementation) for establishing basic level categories on top of data clusterization process. Finally, we test the presented approach against a real bird species dataset, and in comparison to other cluster analysis techniques.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2017

Confidentiality

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

Article name in the collection

2017 13TH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (ICNC-FSKD)

ISBN

978-1-5386-2165-3

ISSN

—

e-ISSN

neuvedeno

Number of pages

8

Pages from-to

400-407

Publisher name

IEEE

Place of publication

NEW YORK

Event location

Guilin, China

Event date

Jul 29, 2017

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000437355300067