リプシッツ定数とアーキテクチャ感度によるニューラルネットワークのロバスト性推定
Estimating Neural Network Robustness via Lipschitz Constant and Architecture Sensitivity
ニューラルネットワークのロバスト性をリプシッツ定数で定量化し、アーキテクチャから解析的に計算する手法を提案。ロボット知覚・意思決定の安全性向上に貢献する。
著者: Abulikemu Abuduweili, Changliu Liu
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Ensuring neural network robustness is essential for the safe and reliable operation of robotic learning systems, especially in perception and decision-making tasks within real-world environments. This paper investigates the robustness of neural networks in perception systems, specifically examining their sensitivity to targeted, small-scale perturbations. We identify the Lipschitz constant as a key metric for quantifying and enhancing network robustness. We derive an analytical expression to compute the Lipschitz constant based on neural network architecture, providing a theoretical basis for estimating and improving robustness. Several experiments reveal the relationship between network design, the Lipschitz constant, and robustness, offering practical insights for developing safer, more robust robot learning systems.
