Noise sensitivity and stability of deep neural networks for binary classification

DOI10.1016/j.spa.2023.08.003zbMath1524.68318arXiv2308.09374OpenAlexW4386102250MaRDI QIDQ6080378

Johan Jonasson, Jeffrey E. Steif, Olof Zetterqvist

Publication date: 30 October 2023

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2308.09374

zbMATH Keywords

Boolean functionsnoise sensitivityfeed-forward neural networksnoise stabilitydeep neural networks

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Artificial neural networks and deep learning (68T07) Interacting random processes; statistical mechanics type models; percolation theory (60K35) Combinatorial probability (60C05) Boolean functions (06E30)

Cites Work

• Quenched Voronoi percolation
• Noise stability of weighted majority
• On the rate of convergence in quenched Voronoi percolation
• Analysis of Boolean Functions
• Partially Observed Boolean Sequences and Noise Sensitivity
• Approximation by superpositions of a sigmoidal function
• Noise sensitivity of Boolean functions and applications to percolation

This page was built for publication: Noise sensitivity and stability of deep neural networks for binary classification