Fixed-Attention Mechanism for Deep-Learning-Assisted Design of High-Degree-of-Freedom 3D Metamaterials
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916668427468800 |
|---|---|
| author | Zhang, Huanshu Kang, Lei Campbell, Sawyer D. Zhang, Kaishun Werner, Douglas H. Cao, Zhaolong |
| author_facet | Zhang, Huanshu Kang, Lei Campbell, Sawyer D. Zhang, Kaishun Werner, Douglas H. Cao, Zhaolong |
| contents | 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 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 apply 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_00203 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fixed-Attention Mechanism for Deep-Learning-Assisted Design of High-Degree-of-Freedom 3D Metamaterials Zhang, Huanshu Kang, Lei Campbell, Sawyer D. Zhang, Kaishun Werner, Douglas H. Cao, Zhaolong Optics 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 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 apply 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. |
| title | Fixed-Attention Mechanism for Deep-Learning-Assisted Design of High-Degree-of-Freedom 3D Metamaterials |
| topic | Optics |
| url | https://arxiv.org/abs/2504.00203 |