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 2405.00532cs.AIcs.LG
收藏

ULLER:一种用于学习与推理的统一语言

ULLER: A Unified Language for Learning and Reasoning

University of Edinburgh(爱丁堡大学);Sony AI(索尼人工智能公司);Fondazione Bruno Kessler(布鲁诺·凯塞勒基金会);UniTrento(特伦托大学);KU Leuven(鲁汶大学);TU Wien(维也纳工业大学)

Emile van Krieken, Samy Badreddine, Robin Manhaeve, Eleonora Giunchiglia

AI总结:

针对神经符号AI框架异构、难以入门和比较的问题,本文提出统一语言ULLER,以神经符号一阶语法涵盖经典、模糊和概率等多种语义,并兼容现有NeSy系统,旨在提升研究的可访问性与可比性。

摘要:

神经符号人工智能(NeSy)领域结合了学习与推理,近年来经历了显著增长。目前存在各种各样的 NeSy 框架,每个框架都有自己特定的语言,用于表达背景知识以及如何将其与神经网络关联起来。这种异构性阻碍了新手的入门,并使比较不同的 NeSy 框架变得困难。我们提出了一种用于 NeSy 的统一语言,称之为 ULLER,即一种用于学习与推理的统一语言。ULLER 涵盖了各种各样的设置,同时确保其中描述的知识可以用于现有的 NeSy 系统。ULLER 具有神经符号一阶语法,我们为其提供了示例语义,包括经典逻辑、模糊逻辑和概率逻辑。我们相信 ULLER 是朝着使 NeSy 研究更易于访问和比较迈出的第一步,为能够在多种语义、知识库和 NeSy 系统之间简化训练和评估的库铺平了道路。

英文摘要:

The field of neuro-symbolic artificial intelligence (NeSy), which combines learning and reasoning, has recently experienced significant growth. There now are a wide variety of NeSy frameworks, each with its own specific language for expressing background knowledge and how to relate it to neural networks. This heterogeneity hinders accessibility for newcomers and makes comparing different NeSy frameworks challenging. We propose a unified language for NeSy, which we call ULLER, a Unified Language for LEarning and Reasoning. ULLER encompasses a wide variety of settings, while ensuring that knowledge described in it can be used in existing NeSy systems. ULLER has a neuro-symbolic first-order syntax for which we provide example semantics including classical, fuzzy, and probabilistic logics. We believe ULLER is a first step towards making NeSy research more accessible and comparable, paving the way for libraries that streamline training and evaluation across a multitude of semantics, knowledge bases, and NeSy systems.

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。

↑