Using Conceptual Spaces for Artificial Intelligence

Please use this identifier to cite or link to this item:
Open Access logo originally created by the Public Library of Science (PLoS)
Title: Using Conceptual Spaces for Artificial Intelligence
Authors: Bechberger, Lucas
Thesis advisor: Prof. Dr. Kai-Uwe Kühnberger
Thesis referee: Prof. Dr. Antonio Lieto
Prof. Dr. Rob Goldstone
Abstract: This dissertation makes the cognitive framework of conceptual spaces (mainly developed by Peter Gärdenfors) usable for practical applications in cognitive AI by providing a thorough mathematical formalization of the framework along with an open source implementation, by proposing and evaluating a novel hybrid approach for connecting raw sensory information to the conceptual layer of representation, and by discussing various learning mechanisms for identifying conceptual regions. It provides a tight integration of various topics such as cognitive AI, neural-symbolic integration, deep representation learning, multidimensional scaling on psychological dissimilarity ratings, and commonsense reasoning.
Subject Keywords: Conceptual Spaces; Machine Learning; Multidimensional Scaling; Cognitive AI; Symbol Grounding
Issue Date: 1-Dec-2023
License name: Attribution 3.0 Germany
License url:
Type of publication: Dissertation oder Habilitation [doctoralThesis]
Appears in Collections:FB08 - E-Dissertationen

Files in This Item:
File Description SizeFormat 
thesis_bechberger.pdfPräsentationsformat44,53 MBAdobe PDF

This item is licensed under a Creative Commons License Creative Commons