Towards conceptual logic tensor networks

Autor(en): Bechberger, L.
Herausgeber: Sanfilippo, E.M.
Kutz, O.
Troquard, N.
Hahmann, T.
Masolo, C.
Hoehndorf, R.
Vita, R.
Hedblom, M.M.
Righetti, G.
Sormaz, D.
Terkaj, W.
Sales, T.P.
de Cesare, S.
Gailly, F.
Guizzardi, G.
Lycett, M.
Partridge, C.
Pastor, O.
Besser, D.
Borgo, S.
Diab, M.
Gangemi, A.
Olivares-Alarcos, A.
Pomarlan, M.
Porzel, R.
Jansen, L.
Brochhausen, M.
Porello, D.
Garbacz, P.
Seppala, S.
Gruninger, M.
Vizedom, A.
Dooley, D.
Warren, R.
McGinty, H.K.
Lange, M.
Algergawy, A.
Karam, N.
Klan, F.
Michel, F.
Rosati, I.
Stichwörter: Artificial intelligence; Cognitive AI; Computer circuits; Conceptual Spaces; Formal ontology; Logic tensor network; Logic Tensor Networks; Membership functions; Memberships function; Neurosymbolic AI; Ontology, Cognitive AI; Real-world; Symbol Grounding; Symbol grounding problem; Symbolic knowledge, Tensors
Erscheinungsdatum: 2021
Herausgeber: CEUR-WS
Enthalten in: CEUR Workshop Proceedings
Band: 2969
The symbol grounding problem refers to the necessity of grounding abstract symbolic knowledge (such as encoded in formal ontologies) in the real world through perception and action. The cognitive framework of conceptual spaces provides a potential way for solving the symbol grounding problem by proposing an intermediate representational layer: Concepts are represented by regions in low-dimensional similarity spaces, which are in turn grounded in subsymbolic processing. Logic tensor networks provide a general mechanism for learning membership functions in the presence of both bottom-up information (i.e., training examples) and top-down constraints in the form of logical rules. In this paper, we propose to combine logic tensor networks with conceptual spaces in order to ground predicates from the symbolic layer in conceptual regions while taking into account logical constraints from abstract background knowledge. We discuss several potential membership functions for concepts and argue that this approach can be used to provide a cognitive grounding for formal ontologies. © 2021 CEUR-WS. All rights reserved.
Conference of Joint Ontology Workshops 2021 Episode VII: The Bolzano Summer of Knowledge, JOWO 2021 ; Conference Date: 11 September 2021 Through 18 September 2021; Conference Code:172257
ISSN: 16130073
Externe URL:

Show full item record

Page view(s)

Last Week
Last month
checked on Jun 25, 2024

Google ScholarTM