Some Geometrical and Topological Properties of DNNs’ Decision Boundaries

Authors: Bo Liu, Mengya Shen
Published: 2020-03-07 | Updated: 2021-04-16

Source: https://arxiv.org/abs/2003.03687

PDF: https://arxiv.org/pdf/2003.03687

AIにより推定されたラベル

数学的基礎 ロバスト性評価 機械学習の基礎

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

Geometry and topology of decision regions are closely related with classification performance and robustness against adversarial attacks. In this paper, we use differential geometry to theoretically explore the geometrical and topological properties of decision regions produced by deep neural networks (DNNs). The goal is to obtain some geometrical and topological properties of decision boundaries for given DNN models, and provide some principled guidance to design and regularization of DNNs. First, we present the curvatures of decision boundaries in terms of network parameters, and give sufficient conditions on network parameters for producing flat or developable decision boundaries. Based on the Gauss-Bonnet-Chern theorem in differential geometry, we then propose a method to compute the Euler characteristics of compact decision boundaries, and verify it with experiments.