arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.04809cs.LGcs.AIcs.CV
收藏

论深度学习的几何性质

On the Geometry of Deep Learning

Brown University(布朗大学);Rice University(莱斯大学)

Randall Balestriero, Ahmed Imtiaz Humayun, Richard Baraniuk

AI总结:

本文综述深度学习数学基础中深度网络与仿射样条函数逼近的关联,梳理相关几何性质(尤其是输入空间剖分)的十年研究,指出该几何视角为分析和改进深度网络提供了有力工具。

摘要:

本文综述了深度学习数学基础中一条颇具前景的进展方向:深度网络与通过仿射样条(多维连续分段线性函数)进行函数逼近之间的关联。我们特别梳理了过去十年间围绕深度网络仿射样条映射的特定几何性质展开的研究,重点关注其对输入空间的剖分方式。正如我们将看到的,仿射样条关联与几何视角提供了一个强有力的切入点,可用于观察、分析并改进深度网络的内部运作机制。

英文摘要:

In this paper, we overview one promising avenue of progress at the mathematical foundation of deep learning: the connection between deep networks and function approximation by affine splines (continuous piecewise linear functions in multiple dimensions). In particular, we will overview work over the past decade on understanding certain geometrical properties of a deep network's affine spline mapping, in particular how it tessellates its input space. As we will see, the affine spline connection and geometrical viewpoint provide a powerful portal through which to view, analyze, and improve the inner workings of a deep network.

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。

↑