FET/SHF: Small: Reinforcement learning and transformer inspired smart photonics inverse design
FET/SHF:小型:强化学习和变压器启发的智能光子逆设计
基本信息
- 批准号:2309403
- 负责人:
- 金额:$ 60万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2023
- 资助国家:美国
- 起止时间:2023-10-01 至 2026-09-30
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
The field of optics and photonics has transformed our lives with such modern technologies as optical communications, solar energy sources, space telescopes and high-resolution photolithography. For a long time, human experts had to perform optical design manually relying on their accumulated experience and physical intuitions. This is especially true for photonic inverse design, where one must find the appropriate photonic structures with the desired optical functions. Recently, deep learning approaches have been pursued by scientific community to automatically design sophisticated structures that can satisfy the design objective, leading to substantial progress in this direction. This research project will enable photonics non-experts to use the developed Artificial Intelligence (AI) model to obtain solutions to their individual optical design problems. Furthermore, understanding the underlying operational principles will advance more generalizable photonics knowledge and enable researchers to develop new structures faster.To accomplish their goals, the research team will explore and apply two powerful AI technologies. The first tool to be studied is deep reinforcement learning, a sequential generation process that learns to design structures with trial-and-reward, in a way to mimic how human and animals learn to interact with the world. Cooperative learning between machine and human will be pursued, where human teaches machine to learn, and machine inspires human to understand. This combined input will benefit the realization of various types of optical structures. The second method utilizes the transformer method, the powerhouse behind the highly successful powerful large language models, for smart optical design. The research team will leverage the Foundation model, the large machine learning models that tackle various downstream tasks once trained on diverse, and large-scale data, to address the optical inverse design of large-scale and complicated nanostructures. The knowledge gained through the study will be applied further to a few testbeds for experimental demonstrations. With more people using the technology and increased data available for training the neural network, one can anticipate its learning and generative capabilities will advance and will the users even more effectively.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
光学和光子学领域通过光通信、太阳能、空间望远镜和高分辨率光刻等现代技术改变了我们的生活。长期以来,人类专家只能依靠自己积累的经验和物理直觉来手动进行光学设计。对于光子逆设计来说尤其如此,人们必须找到具有所需光学功能的合适的光子结构。最近,科学界一直在寻求深度学习的方法来自动设计能够满足设计目标的复杂结构,从而在这个方向上取得了实质性的进展。这一研究项目将使非光子学专家能够使用开发的人工智能(AI)模型来获得他们个人光学设计问题的解决方案。此外,了解潜在的工作原理将推进更普遍的光子学知识,使研究人员能够更快地开发新结构。为了实现他们的目标,研究团队将探索和应用两项强大的人工智能技术。要研究的第一个工具是深度强化学习,这是一种顺序生成过程,学习如何通过试验和奖励来设计结构,以一种模仿人类和动物学习与世界互动的方式。将追求机器与人的合作学习,人教机器学习,机器启发人理解。这种组合输入将有利于实现各种类型的光学结构。第二种方法利用转换器法,这是非常成功的强大的大型语言模型背后的动力源,用于智能光学设计。研究团队将利用基础模型、处理各种下游任务的大型机器学习模型和大规模数据,来解决大规模复杂纳米结构的光学逆向设计。通过研究获得的知识将进一步应用于几个试验台进行实验演示。随着越来越多的人使用这项技术,以及可用于训练神经网络的数据增加,人们可以预期其学习和生成能力将会进步,并将使用户更加有效。该奖项反映了NSF的法定使命,并通过使用基金会的智力优势和更广泛的影响审查标准进行评估,被认为值得支持。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
L. Jay Guo其他文献
Grain engineering for efficient near-infrared perovskite light-emitting diodes
用于高效近红外钙钛矿发光二极管的晶粒工程
- DOI:
10.1038/s41467-024-55075-3 - 发表时间:
2024-12-30 - 期刊:
- 影响因子:15.700
- 作者:
Sung-Doo Baek;Wenhao Shao;Weijie Feng;Yuanhao Tang;Yoon Ho Lee;James Loy;William B. Gunnarsson;Hanjun Yang;Yuchen Zhang;M. Bilal Faheem;Poojan Indrajeet Kaswekar;Harindi R. Atapattu;Jiajun Qin;Aidan H. Coffey;Jee Yung Park;Seok Joo Yang;Yu-Ting Yang;Chenhui Zhu;Kang Wang;Kenneth R. Graham;Feng Gao;Quinn Qiao;L. Jay Guo;Barry P. Rand;Letian Dou - 通讯作者:
Letian Dou
Insight of limitations of effective media theory for metal–dielectric multilayer metamaterials
- DOI:
10.1016/j.optcom.2013.05.005 - 发表时间:
2013-09-15 - 期刊:
- 影响因子:
- 作者:
P. Zhu;P. Jin;L. Jay Guo - 通讯作者:
L. Jay Guo
Application of phase change material in tunable optical filters and shutters
相变材料在可调滤光片和快门中的应用
- DOI:
10.1117/12.2519197 - 发表时间:
2019 - 期刊:
- 影响因子:3.2
- 作者:
M. Jafari;L. Jay Guo;M. Rais - 通讯作者:
M. Rais
Holographic Sampling Display Based on Metagratings
基于元光栅的全息采样显示
- DOI:
10.1016/j.isci.2019.100773 - 发表时间:
2019-12 - 期刊:
- 影响因子:5.8
- 作者:
Wenqiang Wan;Wen Qiao;Donglin Pu;Ruibin Li;Chinhua Wang;Yueqiang Hu;Huigao Duan;L. Jay Guo;Linsen Chen - 通讯作者:
Linsen Chen
Optical multilayer thin film structure inverse design: From optimization to deep learning
光学多层薄膜结构逆向设计:从优化到深度学习
- DOI:
10.1016/j.isci.2025.112222 - 发表时间:
2025-04-18 - 期刊:
- 影响因子:4.100
- 作者:
Taigao Ma;Mingqian Ma;L. Jay Guo - 通讯作者:
L. Jay Guo
L. Jay Guo的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('L. Jay Guo', 18)}}的其他基金
PFI-RP: Artificial colors made sustainable
PFI-RP:人造色素可持续发展
- 批准号:
2213684 - 财政年份:2022
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
I-Corps: A Non-Toxic Electrodeposition Process for Structural Color
I-Corps:一种用于结构颜色的无毒电镀工艺
- 批准号:
1940676 - 财政年份:2019
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
Collaborative Research: Direct, Nozzle-Free Printing of Functional Nanomaterials Using Ultrasound Bubble Cavitation
合作研究:利用超声波气泡空化直接、无喷嘴打印功能纳米材料
- 批准号:
1825945 - 财政年份:2018
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
High-throughput Nano-Scale Patterning for Large-area Nanomanufacturing
用于大面积纳米制造的高通量纳米级图案化
- 批准号:
1537440 - 财政年份:2015
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
I-Corps: Full Color, Low Power, Fast-Response, Reflective Display Technology
I-Corps:全彩、低功耗、快速响应、反射式显示技术
- 批准号:
1530921 - 财政年份:2015
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
I-Corps: Decorative power generation panels and related optoelectronics systems
I-Corps:装饰性发电面板及相关光电系统
- 批准号:
1444843 - 财政年份:2014
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
IDBR: Spectroscopic photoacoustic microscopy for advanced histopathology on living cells and tissues
IDBR:用于活细胞和组织高级组织病理学的光谱光声显微镜
- 批准号:
1256001 - 财政年份:2013
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
GOALI: Wire Grid Color Filters for Energy Efficient Displays
GOALI:用于节能显示器的线栅滤色片
- 批准号:
1202046 - 财政年份:2012
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
SNM: Continuous and Large Scale Nanomanufacturing of Graphene and Carbon Nanotube Materials
SNM:石墨烯和碳纳米管材料的连续大规模纳米制造
- 批准号:
1120187 - 财政年份:2011
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
Nanomanufacturing Process and Applications Based on Dynamic Nano-Inscribing
基于动态纳米刻划的纳米制造工艺及应用
- 批准号:
1000425 - 财政年份:2010
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
相似国自然基金
天然超短抗菌肽Temporin-SHf衍生多肽的构效分析与抗菌机制研究
- 批准号:
- 批准年份:2024
- 资助金额:0.0 万元
- 项目类别:省市级项目
衔接蛋白SHF负向调控胶质母细胞瘤中EGFR/EGFRvIII再循环和稳定性的功能及机制研究
- 批准号:82302939
- 批准年份:2023
- 资助金额:30 万元
- 项目类别:青年科学基金项目
EGFR/GRβ/Shf调控环路在胶质瘤中的作用机制研究
- 批准号:81572468
- 批准年份:2015
- 资助金额:60.0 万元
- 项目类别:面上项目
相似海外基金
Collaborative Research: SHF: Small: LEGAS: Learning Evolving Graphs At Scale
协作研究:SHF:小型:LEGAS:大规模学习演化图
- 批准号:
2331302 - 财政年份:2024
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Small: LEGAS: Learning Evolving Graphs At Scale
协作研究:SHF:小型:LEGAS:大规模学习演化图
- 批准号:
2331301 - 财政年份:2024
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Small: Efficient and Scalable Privacy-Preserving Neural Network Inference based on Ciphertext-Ciphertext Fully Homomorphic Encryption
合作研究:SHF:小型:基于密文-密文全同态加密的高效、可扩展的隐私保护神经网络推理
- 批准号:
2412357 - 财政年份:2024
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
SHF: Small: Taming Huge Page Problems for Memory Bulk Operations Using a Hardware/Software Co-Design Approach
SHF:小:使用硬件/软件协同设计方法解决内存批量操作的大页面问题
- 批准号:
2400014 - 财政年份:2024
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
SHF: SMALL: A New Semantics for Type-Level Programming in Haskell
SHF:SMALL:Haskell 中类型级编程的新语义
- 批准号:
2345580 - 财政年份:2024
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
SHF: Small: QED - A New Approach to Scalable Verification of Hardware Memory Consistency
SHF:小型:QED - 硬件内存一致性可扩展验证的新方法
- 批准号:
2332891 - 财政年份:2024
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
SHF: Small: Redesigning the Memory System in the Era of Compute Express Link
SHF:小型:重新设计 Compute Express Link 时代的内存系统
- 批准号:
2333049 - 财政年份:2024
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
SHF: Small: Hardware-Software Co-design for Privacy Protection on Deep Learning-based Recommendation Systems
SHF:小型:基于深度学习的推荐系统的隐私保护软硬件协同设计
- 批准号:
2334628 - 财政年份:2024
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
Conference: SHF: Small: NSF Student Travel Grant for 2024 IEEE VLSI Test Symposium
会议:SHF:小型:2024 年 IEEE VLSI 测试研讨会 NSF 学生旅费补助金
- 批准号:
2334367 - 财政年份:2024
- 资助金额:
$ 60万 - 项目类别:
Standard Grant
SHF: Small: Semi-supervised Learning for Design and Quality Assurance of Integrated Circuits
SHF:小型:集成电路设计和质量保证的半监督学习
- 批准号:
2334380 - 财政年份:2024
- 资助金额:
$ 60万 - 项目类别:
Standard Grant