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 2007.07320cs.LGcs.AIstat.ML
收藏

用欧拉神经网络学习三段论

Learning Syllogism with Euler Neural-Networks

University of Bonn(波恩大学);Tsinghua University(清华大学)

Tiansi Dong, Chengjiang Li, Christian Bauckhage, Juanzi Li, Stefan Wrobel, Armin B. Cremers

摘要:

传统的神经网络将所有事物表示为向量,并且能够在一定程度上近似逻辑推理的子集。由于区域之间的拓扑关系更好地表示基本逻辑关系,我们提出了一种新的神经网络,表示一切作为一个球,并能够学习拓扑结构作为欧拉图。欧拉神经网络(Euler Neural Network,ENN)球的中心向量是一个可以继承传统神经网络的表示能力的向量。ENN区分了球之间的四种空间状态,即断开、部分重叠、是的一部分、是的反部分。在每个状态中,定义理想值以进行有效推理。提出了一种新的基于六个空间单元的反向传播算法(ReSU),该算法可以优化表示逻辑前提的欧拉图,并从欧拉图中推导出逻辑结论。与传统的神经网络相比,ENN能够精确地表示三段论的所有24种不同结构。创建了两个大型数据集:一个从WordNet-3.0中提取,涵盖了所有类型的三段论推理,另一个从DBpedia中提取了所有的家族关系。实验结果证明了ENN在逻辑表示和推理方面的优越性。数据集和源代码可应要求提供。

英文摘要:

Traditional neural networks represent everything as a vector, and are able to approximate a subset of logical reasoning to a certain degree. As basic logic relations are better represented by topological relations between regions, we propose a novel neural network that represents everything as a ball and is able to learn topological configuration as an Euler diagram. So comes the name Euler Neural-Network (ENN). The central vector of a ball is a vector that can inherit representation power of traditional neural network. ENN distinguishes four spatial statuses between balls, namely, being disconnected, being partially overlapped, being part of, being inverse part of. Within each status, ideal values are defined for efficient reasoning. A novel back-propagation algorithm with six Rectified Spatial Units (ReSU) can optimize an Euler diagram representing logical premises, from which logical conclusion can be deduced. In contrast to traditional neural network, ENN can precisely represent all 24 different structures of Syllogism. Two large datasets are created: one extracted from WordNet-3.0 covers all types of Syllogism reasoning, the other extracted all family relations from DBpedia. Experiment results approve the superior power of ENN in logical representation and reasoning. Datasets and source code are available upon request.

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。

↑