Towards Grounding Conceptual Spaces in Neural Representations

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.

accepted at NeSy 2017; The final version of this paper is available at http://ceur-ws.org/Vol-2003/

References in corpus (2)

• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• Energy-based Generative Adversarial Network