arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.03573cs.AIcs.NEcs.SC
收藏

神经类比匹配

Neural Analogical Matching

Northwestern University(西北大学);IBM Research(IBM研究院)

Maxwell Crouse, Constantine Nakos, Ibrahim Abdelaziz, Kenneth Forbus

摘要:

类比是人类认知的核心。它允许我们根据先前的经验解决问题,它支配着我们对新信息的概念化方式,甚至影响我们的视觉感知。类比对人类的重要性使其成为更广泛的人工智能研究领域的一个活跃领域,从而产生了以类似人类的方式学习和推理的数据高效模型。虽然类比和深度学习的认知视角通常是相互独立的,但这两条研究路线的整合是朝着更强大和更有效的学习技术迈出的有希望的一步。作为对这种整合的越来越多的研究的一部分,我们引入了类比匹配网络:一种神经架构,它学习在结构化的符号表示之间产生类比,这些表示在很大程度上与结构映射理论的原则一致。

英文摘要:

Analogy is core to human cognition. It allows us to solve problems based on prior experience, it governs the way we conceptualize new information, and it even influences our visual perception. The importance of analogy to humans has made it an active area of research in the broader field of artificial intelligence, resulting in data-efficient models that learn and reason in human-like ways. While cognitive perspectives of analogy and deep learning have generally been studied independently of one another, the integration of the two lines of research is a promising step towards more robust and efficient learning techniques. As part of a growing body of research on such an integration, we introduce the Analogical Matching Network: a neural architecture that learns to produce analogies between structured, symbolic representations that are largely consistent with the principles of Structure-Mapping Theory.

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。

↑