arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.13697cs.LGcs.CGmath.ATstat.ML
收藏

一个用于深度学习的拓扑框架

A Topological Framework for Deep Learning

Santa Clara University(圣克拉拉大学)

Mustafa Hajij, Kyle Istvan

摘要:

我们利用经典的事实,从拓扑结构表明,分类问题在机器学习总是可以解决的非常温和的条件下。此外,我们证明了softmax分类网络通过有限的拓扑移动序列作用于输入拓扑空间以实现分类任务。此外,给定一个训练数据集,我们展示了如何拓扑形式主义可以用来建议适当的架构选择神经网络设计的数据上的分类器进行训练。最后,我们展示了神经网络的架构如何不能独立于底层数据的形状来选择。为了证明这些结果,我们提供了示例数据集,并从拓扑角度展示了神经网络如何对它们进行操作。

英文摘要:

We utilize classical facts from topology to show that the classification problem in machine learning is always solvable under very mild conditions. Furthermore, we show that a softmax classification network acts on an input topological space by a finite sequence of topological moves to achieve the classification task. Moreover, given a training dataset, we show how topological formalism can be used to suggest the appropriate architectural choices for neural networks designed to be trained as classifiers on the data. Finally, we show how the architecture of a neural network cannot be chosen independently from the shape of the underlying data. To demonstrate these results, we provide example datasets and show how they are acted upon by neural nets from this topological perspective.

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。

↑