On the benefit of attention in inverse design of thin films filters
Open Access
- 5 August 2024
- journal article
- research article
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 5 (3) , 035034
Abstract
Attention layers are a crucial component in many modern deep learning models, particularly those used in natural language processing and computer vision. Attention layers have been shown to improve the accuracy and effectiveness of various tasks, such as machine translation, image captioning, etc. Here, the benefit of attention layers in designing optical filters based on a stack of thin film materials is investigated. The superiority of Attention layers over fully-connected Deep Neural Networks is demonstrated for this task.Keywords
This publication has 40 references indexed in Scilit:
- Attention, please! A survey of neural attention models in deep learningArtificial Intelligence Review, 2022
- Deep Learning the Electromagnetic Properties of Metamaterials—A Comprehensive ReviewAdvanced Functional Materials, 2021
- Deep Learning to Accelerate Scatterer-to-Field Mapping for Inverse Design of Dielectric MetasurfacesACS Photonics, 2021
- Tackling Photonic Inverse Design with Machine LearningAdvanced Science, 2021
- Deep Convolutional Mixture Density Network for Inverse Design of Layered Photonic StructuresACS Photonics, 2020
- Elucidating the Behavior of Nanophotonic Structures through Explainable Machine Learning AlgorithmsACS Photonics, 2020
- Inverse design of metasurface optical filters using deep neural network with high degrees of freedomInfoMat, 2020
- An Introductory Survey on Attention Mechanisms in NLP Problems2019
- Generative Model for the Inverse Design of MetasurfacesNano Letters, 2018
- Deep-Learning-Enabled On-Demand Design of Chiral MetamaterialsACS Nano, 2018