Frontiers

Graph Learning and Deep Unfolding for Electromagnetic Field Modelling and Antenna Systems

Traditional computational electromagnetics (CEM) methods—such as MoM, FEM, or FDTD—offer high fidelity, but struggle to scale ...
IEEE

BLTOO-MFFL: Automated and Adversarially Robust Deep Learning for SAR Image Classification by Bi-Level Three-Objective Optimization and Multi-Feature Fusion Loss

Abstract: The deep learning-based synthetic aperture radar (SAR) image classification model is vulnerable to adversarial attacks. Although automated deep learning (ADL) including neural architecture ...
IEEE

Deep Learning-Based Design of Metasurface Transmitarray Elements with Adjustable Phase and Amplitude Characteristics

Abstract: A deep learning-based approach is proposed for the rapid design of metasurface transmitarray elements with adjustable phase and amplitude response characteristics. This method leverages a ...

A Flat Optical Surface Just Broke a Major Rule of Light

Dispersion is an inherent feature of electromagnetic waves. It allows light to behave differently at different wavelengths, ...