Towards grounding conceptual spaces in neural representations
Autor(en): | Bechberger, L. Kühnberger, K.-U. |
Herausgeber: | Besold, T.R. Noble, I. d'Avila Garcez, A. |
Stichwörter: | Conceptual spaces; High dimensional spaces; Neural representations; Sub-symbolic; Unlabeled data | Erscheinungsdatum: | 2017 | Herausgeber: | CEUR-WS | Journal: | CEUR Workshop Proceedings | Volumen: | 2003 | Zusammenfassung: | The highly influential framework of conceptual spaces provides a geometric way of representing knowledge. It aims at bridging the gap between symbolic and subsymbolic processing. Instances are represented by points in a high-dimensional space and concepts are represented by convex regions in this space. In this paper, we present our approach towards grounding the dimensions of a conceptual space in latent spaces learned by an InfoGAN from unlabeled data. Copyright © 2017 for this paper by its authors. |
Beschreibung: | Conference of 12th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2017 ; Conference Date: 17 July 2017 Through 18 July 2017; Conference Code:132032 |
ISSN: | 16130073 | Externe URL: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85037115832&partnerID=40&md5=12c0cdbe39a2b18bfbcc0011485527d7 |
Zur Langanzeige