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 2604.24672cs.LGmath.AT
收藏

邻域聚合深度学习的函子化表述

A Functorial Formulation of Neighborhood Aggregating Deep Learning

Max Planck Institute for Mathematics(马克斯·普朗克数学研究所);Korea Advanced Institute of Science and Technology(韩国科学技术院);National Institute for Mathematical Sciences(数学科学研究院)

Sun Woo Park, Yun Young Choi, U Jin Choi, Youngho Woo

AI总结:

本文通过拓扑空间上连续函数集的预层和后层,数学化解释卷积神经网络,并提出理论启发,揭示其经验限制。

摘要:

我们通过拓扑空间上连续函数集的预层和后层,对卷积(或信息传递)神经网络进行数学解释。基于此解释,我们提出一个理论启发,通过拓扑空间上连续函数集作为层或后层的障碍,阐述这些神经网络的若干经验限制。

英文摘要:

We provide a mathematical interpretation of convolutional (or message passing) neural networks by using presheaves and copresheaves of the set of continuous functions over a topological space. Based on this interpretation, we formulate a theoretical heuristic which elaborates a number of empirical limitations of these neural networks by using obstructions on such sets of continuous functions over a topological space to be sheaves or copresheaves.

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。

↑