光学神经网络：进展与挑战。

IF 3.5 3区医学 Q2 CHEMISTRY, MEDICINAL

ACS Medicinal Chemistry Letters Pub Date : 2024-09-20 DOI:10.1038/s41377-024-01590-3

Tingzhao Fu,Jianfa Zhang,Run Sun,Yuyao Huang,Wei Xu,Sigang Yang,Zhihong Zhu,Hongwei Chen

{"title":"光学神经网络：进展与挑战。","authors":"Tingzhao Fu,Jianfa Zhang,Run Sun,Yuyao Huang,Wei Xu,Sigang Yang,Zhihong Zhu,Hongwei Chen","doi":"10.1038/s41377-024-01590-3","DOIUrl":null,"url":null,"abstract":"Artificial intelligence has prevailed in all trades and professions due to the assistance of big data resources, advanced algorithms, and high-performance electronic hardware. However, conventional computing hardware is inefficient at implementing complex tasks, in large part because the memory and processor in its computing architecture are separated, performing insufficiently in computing speed and energy consumption. In recent years, optical neural networks (ONNs) have made a range of research progress in optical computing due to advantages such as sub-nanosecond latency, low heat dissipation, and high parallelism. ONNs are in prospect to provide support regarding computing speed and energy consumption for the further development of artificial intelligence with a novel computing paradigm. Herein, we first introduce the design method and principle of ONNs based on various optical elements. Then, we successively review the non-integrated ONNs consisting of volume optical components and the integrated ONNs composed of on-chip components. Finally, we summarize and discuss the computational density, nonlinearity, scalability, and practical applications of ONNs, and comment on the challenges and perspectives of the ONNs in the future development trends.","PeriodicalId":20,"journal":{"name":"ACS Medicinal Chemistry Letters","volume":"35 1","pages":"263"},"PeriodicalIF":3.5000,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Optical neural networks: progress and challenges.\",\"authors\":\"Tingzhao Fu,Jianfa Zhang,Run Sun,Yuyao Huang,Wei Xu,Sigang Yang,Zhihong Zhu,Hongwei Chen\",\"doi\":\"10.1038/s41377-024-01590-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Artificial intelligence has prevailed in all trades and professions due to the assistance of big data resources, advanced algorithms, and high-performance electronic hardware. However, conventional computing hardware is inefficient at implementing complex tasks, in large part because the memory and processor in its computing architecture are separated, performing insufficiently in computing speed and energy consumption. In recent years, optical neural networks (ONNs) have made a range of research progress in optical computing due to advantages such as sub-nanosecond latency, low heat dissipation, and high parallelism. ONNs are in prospect to provide support regarding computing speed and energy consumption for the further development of artificial intelligence with a novel computing paradigm. Herein, we first introduce the design method and principle of ONNs based on various optical elements. Then, we successively review the non-integrated ONNs consisting of volume optical components and the integrated ONNs composed of on-chip components. Finally, we summarize and discuss the computational density, nonlinearity, scalability, and practical applications of ONNs, and comment on the challenges and perspectives of the ONNs in the future development trends.\",\"PeriodicalId\":20,\"journal\":{\"name\":\"ACS Medicinal Chemistry Letters\",\"volume\":\"35 1\",\"pages\":\"263\"},\"PeriodicalIF\":3.5000,\"publicationDate\":\"2024-09-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACS Medicinal Chemistry Letters\",\"FirstCategoryId\":\"1089\",\"ListUrlMain\":\"https://doi.org/10.1038/s41377-024-01590-3\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CHEMISTRY, MEDICINAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Medicinal Chemistry Letters","FirstCategoryId":"1089","ListUrlMain":"https://doi.org/10.1038/s41377-024-01590-3","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, MEDICINAL","Score":null,"Total":0}

引用次数: 0

摘要

在大数据资源、先进算法和高性能电子硬件的帮助下，人工智能在各行各业大行其道。然而，传统计算硬件在执行复杂任务时效率低下，很大程度上是因为其计算架构中的内存和处理器是分离的，在运算速度和能耗方面表现不足。近年来，光神经网络（ONNs）凭借亚纳秒级延迟、低散热和高并行性等优势，在光计算领域取得了一系列研究进展。ONNs有望在计算速度和能源消耗方面为人工智能的进一步发展提供支持，成为一种新的计算模式。在此，我们首先介绍了基于各种光学元件的 ONN 的设计方法和原理。然后，我们依次回顾了由体积光学元件组成的非集成 ONN 和由片上元件组成的集成 ONN。最后，我们总结并讨论了 ONNs 的计算密度、非线性、可扩展性和实际应用，并对 ONNs 在未来发展趋势中面临的挑战和前景进行了评论。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Optical neural networks: progress and challenges.

Artificial intelligence has prevailed in all trades and professions due to the assistance of big data resources, advanced algorithms, and high-performance electronic hardware. However, conventional computing hardware is inefficient at implementing complex tasks, in large part because the memory and processor in its computing architecture are separated, performing insufficiently in computing speed and energy consumption. In recent years, optical neural networks (ONNs) have made a range of research progress in optical computing due to advantages such as sub-nanosecond latency, low heat dissipation, and high parallelism. ONNs are in prospect to provide support regarding computing speed and energy consumption for the further development of artificial intelligence with a novel computing paradigm. Herein, we first introduce the design method and principle of ONNs based on various optical elements. Then, we successively review the non-integrated ONNs consisting of volume optical components and the integrated ONNs composed of on-chip components. Finally, we summarize and discuss the computational density, nonlinearity, scalability, and practical applications of ONNs, and comment on the challenges and perspectives of the ONNs in the future development trends.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

ACS Medicinal Chemistry Letters CHEMISTRY, MEDICINAL-

CiteScore

7.30

自引率

2.40%

发文量

328

审稿时长

1 months

期刊介绍： ACS Medicinal Chemistry Letters is interested in receiving manuscripts that discuss various aspects of medicinal chemistry. The journal will publish studies that pertain to a broad range of subject matter, including compound design and optimization, biological evaluation, drug delivery, imaging agents, and pharmacology of both small and large bioactive molecules. Specific areas include but are not limited to: Identification, synthesis, and optimization of lead biologically active molecules and drugs (small molecules and biologics) Biological characterization of new molecular entities in the context of drug discovery Computational, cheminformatics, and structural studies for the identification or SAR analysis of bioactive molecules, ligands and their targets, etc. Novel and improved methodologies, including radiation biochemistry, with broad application to medicinal chemistry Discovery technologies for biologically active molecules from both synthetic and natural (plant and other) sources Pharmacokinetic/pharmacodynamic studies that address mechanisms underlying drug disposition and response Pharmacogenetic and pharmacogenomic studies used to enhance drug design and the translation of medicinal chemistry into the clinic Mechanistic drug metabolism and regulation of metabolic enzyme gene expression Chemistry patents relevant to the medicinal chemistry field.