Robust Method
Robust methods in machine learning aim to develop algorithms and models that maintain high performance despite noisy data, adversarial attacks, or other uncertainties. Current research focuses on improving robustness across diverse applications, including image analysis (using techniques like atlas registration and diffusion models), regression (addressing the bias-variance trade-off), and deep learning (e.g., through multi-module architectures and loss function modifications). These advancements are crucial for enhancing the reliability and trustworthiness of AI systems in various fields, from medical image analysis and remote sensing to cybersecurity and reliable engineering design.
17papers
Papers
March 20, 2025
February 27, 2025
December 15, 2024
October 23, 2024
October 3, 2024
July 15, 2024
June 10, 2024
February 14, 2024
March 8, 2023
February 19, 2023
September 16, 2022
August 10, 2022