A novel framework for symbol grounding in artificial agents is presented, which relies on the key idea that concepts "emerge" implicitly at the perceptual level as clusters of points with similar features forming homogeneous regions in multiple perceptual Conceptual Spaces (pCS). Such spaces describe percepts such as color, texture, shape, and position that in turn are the properties of the objects populating the agent's environment. Objects are represented in a suitable object Conceptual Space where all their features are composed together again using clustering in pCSs. Symbols will be learned from such a tensor space. A detailed description of both the framework and its theoretical foundations are reported and discussed in this work.

Pirrone, R., Chella, A. (2018). Grounding concepts as emerging clusters in multiple conceptual spaces. In CEUR Workshop Proceedings. CEUR-WS.

Grounding concepts as emerging clusters in multiple conceptual spaces

Pirrone, Roberto;Chella, Antonio
2018-01-01

Abstract

A novel framework for symbol grounding in artificial agents is presented, which relies on the key idea that concepts "emerge" implicitly at the perceptual level as clusters of points with similar features forming homogeneous regions in multiple perceptual Conceptual Spaces (pCS). Such spaces describe percepts such as color, texture, shape, and position that in turn are the properties of the objects populating the agent's environment. Objects are represented in a suitable object Conceptual Space where all their features are composed together again using clustering in pCSs. Symbols will be learned from such a tensor space. A detailed description of both the framework and its theoretical foundations are reported and discussed in this work.
2018
Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazioni
Pirrone, R., Chella, A. (2018). Grounding concepts as emerging clusters in multiple conceptual spaces. In CEUR Workshop Proceedings. CEUR-WS.
File in questo prodotto:
File Dimensione Formato  
paper15.pdf

accesso aperto

Tipologia: Versione Editoriale
Dimensione 514.69 kB
Formato Adobe PDF
514.69 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10447/339840
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact