神经网络中的非参数拓扑层
Nonparametric Topological Layers in Neural Networks
摘要:
各种拓扑技术和工具已被应用到神经网络的网络复杂性,可解释性和性能方面。这条研究路线的一个基本假设是存在一个全局(欧几里德)坐标系,在该坐标系上构建拓扑层。尽管有有希望的结果,但这种\textit{topologization}方法尚未被广泛采用,因为拓扑化层的参数化花费相当多的时间,更重要的是,缺乏理论基础,没有该理论基础,神经网络的性能仅达到次优性能。本文提出了一种用于神经网络的可学习拓扑层,而不需要欧几里得空间;相反,所提出的构造只需要一个一般度量空间,除了内积,即,希尔伯特空间因此,所提出的拓扑层的相应参数化是免费的用户指定的超参数,这排除了昂贵的参数化阶段和相应的次优网络的可能性。
英文摘要:
Various topological techniques and tools have been applied to neural networks in terms of network complexity, explainability, and performance. One fundamental assumption of this line of research is the existence of a global (Euclidean) coordinate system upon which the topological layer is constructed. Despite promising results, such a \textit{topologization} method has yet to be widely adopted because the parametrization of a topologization layer takes a considerable amount of time and more importantly, lacks a theoretical foundation without which the performance of the neural network only achieves suboptimal performance. This paper proposes a learnable topological layer for neural networks without requiring a Euclidean space; Instead, the proposed construction requires nothing more than a general metric space except for an inner product, i.e., a Hilbert space. Accordingly, the according parametrization for the proposed topological layer is free of user-specified hyperparameters, which precludes the costly parametrization stage and the corresponding possibility of suboptimal networks.
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。