Search

Your search keyword '"Xu, Yuelin"' showing total 4 results
Start Over Author "Xu, Yuelin" Publication Year Range This year
4 results on '"Xu, Yuelin"'

1. Understanding Adversarially Robust Generalization via Weight-Curvature Index

Author

Xu, Yuelin and Zhang, Xiao

Subjects
Computer Science - Machine Learning
Abstract

Despite extensive research on adversarial examples, the underlying mechanisms of adversarially robust generalization, a critical yet challenging task for deep learning, remain largely unknown. In this work, we propose a novel perspective to decipher adversarially robust generalization through the lens of the Weight-Curvature Index (WCI). The proposed WCI quantifies the vulnerability of models to adversarial perturbations using the Frobenius norm of weight matrices and the trace of Hessian matrices. We prove generalization bounds based on PAC-Bayesian theory and second-order loss function approximations to elucidate the interplay between robust generalization gap, model parameters, and loss landscape curvature. Our theory and experiments show that WCI effectively captures the robust generalization performance of adversarially trained models. By offering a nuanced understanding of adversarial robustness based on the scale of model parameters and the curvature of the loss landscape, our work provides crucial insights for designing more resilient deep learning models, enhancing their reliability and security.

Published
2024

4. Research on the Inversion of Chlorophyll-a Concentration in the Hong Kong Coastal Area Based on Convolutional Neural Networks.

Author

Zhu, Weidong, Liu, Shuai, Luan, Kuifeng, Xu, Yuelin, Liu, Zitao, Cao, Tiantian, and Wang, Piao

Subjects
MACHINE learning, CONVOLUTIONAL neural networks, TERRITORIAL waters, BODIES of water, THEMATIC maps
Abstract

Chlorophyll-a (Chl-a) concentration is a key indicator for assessing the eutrophication level in water bodies. However, accurately inverting Chl-a concentrations in optically complex coastal waters presents a significant challenge for traditional models. To address this, we employed Sentinel-2 MSI sensor data and leveraged the power of five machine learning models, including a convolutional neural network (CNN), to enhance the inversion process in the coastal waters near Hong Kong. The CNN model demonstrated superior performance with on-site data validation, outperforming the other four models (R2 = 0.810, RMSE = 1.165 μg/L, MRE = 35.578%). The CNN model was employed to estimate Chl-a concentrations from images captured over the study area in April and October 2022, resulting in the creation of a thematic map illustrating the spatial distribution of Chl-a levels. The map indicated high Chl-a concentrations in the northeast and southwest areas of Hong Kong Island and low Chl-a concentrations in the southeast facing the open sea. Analysis of patch size effects on CNN model accuracy indicated that 7 × 7 and 9 × 9 patches yielded the most optimal results across the tested sizes. Shapley additive explanations were employed to provide post-hoc interpretations for the best-performing CNN model, highlighting that features B6, B12, and B8 were the most important during the inversion process. This study can serve as a reference for developing machine learning models to invert water quality parameters. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results