Fixed-attention mechanism for deep-learning-assisted design of high-degree-of-freedom 3D metamaterials

The traditional design approaches for high-degree-of-freedom metamaterials have been computationally intensive and, in many cases, even intractable due to the vast design space. In this work, we introduce what we believe to be a novel fixed-attention mechanism into a deep learning framework to address the computational challenges of metamaterial design. We consider a 3D plasmonic structure composed of gold nanorods characterized by geometric parameters and demonstrate that a long short-term memory network with a fixed-attention mechanism can improve the prediction accuracy by 48.09% compared to networks without attention. Additionally, we successfully applied this framework for the inverse design of plasmonic metamaterials. Our approach significantly reduces computational costs, opening the door for efficient real-time optimization of complex nanostructures.