A Stability Analysis of Neural Networks and Its Application to Tsunami Early Warning
Journal of Geophysical Research: Machine Learning and Computation · 2024-12 · 1 (4)
DOI: 10.1029/2024jh000223 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Geophysical Research: Machine Learning and Computation, online erschienen am 05.12.2024. Verfasst von Donsub Rim und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Neural networks (NNs) enable precise modeling of complicated geophysical phenomena but can be sensitive to small input changes. In this work, we present a new method for analyzing this instability in NNs. We focus our analysis on adversarial examples, test‐time inputs with carefully crafted human‐imperceptible perturbations that expose the worst‐case instability in a model's predictions. Our stability analysis is based on a low‐rank expansion of NNs on a fixed input, and we apply our analysis to a NN model for tsunami early warning which takes geodetic measurements as the input and forecasts tsunami waveforms. The result is an improved description of local stability that explains adversarial examples generated by a standard gradient‐based algorithm, and allows the generation of other comparable examples. Our analysis can predict whether noise in the geodetic input will produce an unstable output, and identifies a potential approach to filtering the input that enable more robust forecasting.
Zitieren
APA
Rim, D., Suri, S., Hong, S., Lee, K., & LeVeque, R. J. (2024). A Stability Analysis of Neural Networks and Its Application to Tsunami Early Warning. Journal of Geophysical Research: Machine Learning and Computation, 1(4). https://doi.org/10.1029/2024jh000223
Vancouver
Rim D, Suri S, Hong S, Lee K, LeVeque RJ. A Stability Analysis of Neural Networks and Its Application to Tsunami Early Warning. Journal of Geophysical Research: Machine Learning and Computation. 2024;1(4). doi:10.1029/2024jh000223
BibTeX
@article{Rim2024,
author = {Rim, Donsub and Suri, Sanah and Hong, Sanghyun and Lee, Kookjin and LeVeque, Randall J.},
title = {A Stability Analysis of Neural Networks and Its Application to Tsunami Early Warning},
journal = {Journal of Geophysical Research: Machine Learning and Computation},
year = {2024},
volume = {1},
number = {4},
doi = {10.1029/2024jh000223}
}
EUVIMED