Mapping images to psychological similarity spaces using neural networks

Autor(en): Bechberger, L.
Kypridemou, E.
Herausgeber: Chella, A.
Infantino, I.
Lieto, A.
Stichwörter: Conceptual spaces; Feasibility studies; Machine learning; Machine learning techniques; Multi-dimensional scaling; Multidimensional scaling; Neural networks; Neural networks, Cognitive frameworks; Psychological experiment; Similarity spaces; Sub-symbolic, Mapping
Erscheinungsdatum: 2019
Herausgeber: CEUR-WS
Enthalten in: CEUR Workshop Proceedings
Band: 2418
Startseite: 26
Seitenende: 39
Zusammenfassung: 
The cognitive framework of conceptual spaces bridges the gap between symbolic and subsymbolic AI by proposing an intermediate conceptual layer where knowledge is represented geometrically. There are two main approaches for obtaining the dimensions of this conceptual similarity space: using similarity ratings from psychological experiments and using machine learning techniques. In this paper, we propose a combination of both approaches by using psychologically derived similarity ratings to constrain the machine learning process. This way, a mapping from stimuli to conceptual spaces can be learned that is both supported by psychological data and allows generalization to unseen stimuli. The results of a first feasibility study support our proposed approach. © 2019 CEUR-WS. All rights reserved.
Beschreibung: 
Conference of 6th International Workshop on Artificial Intelligence and Cognition, AIC 2018 ; Conference Date: 2 July 2018 Through 4 July 2018; Conference Code:149886
ISSN: 16130073
Externe URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85071307910&partnerID=40&md5=723875691ac305f888efbd2f73e7494a

Show full item record

Google ScholarTM

Check