arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1706.04825cs.AI
收藏

神经表征中的概念空间基础

Towards Grounding Conceptual Spaces in Neural Representations

Osnabrück University(奥斯纳布吕克大学)

Lucas Bechberger, Kai-Uwe Kühnberger

摘要:

概念空间的高度影响力的框架提供了一个几何的方式来表示知识。它旨在弥合符号和次符号处理之间的差距。在高维空间中,概念由点表示,概念由该空间中的凸区域表示。在本文中,我们提出了我们的方法,通过InfoGAN从未标记的数据中学习到的潜在空间中的概念空间的维度。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑