Functional concept acquisition using action schemata

Author

Wazlawick, Raul Sidnei

Author_Institution

Dept. de Inf. e Estatistica, Univ. Federal de Santa Catarina, Florianapolis, Brazil

fYear

35765

fDate

8-10 Dec1997

Firstpage

282

Lastpage

286

Abstract

This paper discusses unsupervised concept acquisition in autonomous agents. Autonomous agents build their knowledge from action and perception in their environment. A structure inspired in Piaget´s schema mechanism was used in order to represent functional concepts, that is, concepts related to conditions, actions and results. This kind of mechanism was first implemented by Dresher (1992). This paper presents a new approach that uses a kind of competitive neural network (the Schemata) to find the condition/action/result correlation when the concepts are presented as fuzzy signals

Keywords

fuzzy logic; knowledge acquisition; neural nets; software agents; uncertainty handling; unsupervised learning; Schemata; action schemata; autonomous agents; competitive neural network; functional concept acquisition; fuzzy signals; knowledge acquisition; perception; schema mechanism; unsupervised concept acquisition; Autonomous agents; Fuzzy neural networks; Knowledge acquisition; Neural networks; Neurons; Sensor phenomena and characterization; Sensor systems; Signal processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Information Systems, 1997. IIS '97. Proceedings

Conference_Location

Grand Bahama Island

Print_ISBN

0-8186-8218-3

Type

conf

DOI

10.1109/IIS.1997.645257

Filename

645257