Towards Grounding Conceptual Spaces in Neural Representations
Artificial Intelligence
2017-11-22 v2
Abstract
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.
Cite
@article{arxiv.1706.04825,
title = {Towards Grounding Conceptual Spaces in Neural Representations},
author = {Lucas Bechberger and Kai-Uwe Kühnberger},
journal= {arXiv preprint arXiv:1706.04825},
year = {2017}
}
Comments
accepted at NeSy 2017; The final version of this paper is available at http://ceur-ws.org/Vol-2003/