11-19 更新 实时
首页/ 算力/ 正文

要有光:新型 AI 框架运行在光学硬件上

算力 来源:TechXplore 2026-11-05 18:00 0 阅读 机器翻译
要有光:新型 AI 框架运行在光学硬件上

由 Gaby Clark 编辑,Robert Egan 审阅

本文已按照 Science X 的编辑流程与政策进行审核。编辑在确保内容可信度的同时,重点标明了以下属性:

经同行评审的出版物

添加到首选来源

在用于演示单映射方法的光计算系统中,信息被转换为光信号,在通过光纤环路时得到处理,随后再转换回电信号以供分析。该系统使用一根 200 米长的光纤和少量电子元件来执行 AI 计算。图片来源:2026 Nakajima 等,CC-BY-ND

人工智能正日益普及、能力不断增强,但同时也极其耗电。包括东京大学研究人员在内的研究团队开发出一种构建基于物理的 AI 的新方法——这类系统利用物理系统的自然行为来处理信息——可大幅减少其运行所需的计算量。该方法同时简化了这类系统的学习方式和结构。研究团队用一个以光来处理信息的光计算系统进行了演示,这可能有助于为更快、更节能的 AI 硬件铺平道路。

AI 的存在很难被忽视。即便你不直接与 AI 系统交互,新闻报道和软件也不断让人感受到它的存在。在幕后,AI 系统正变得更大、更复杂,也更消耗资源。在围绕 AI 增长的诸多担忧中,最突出的一项就是运行这些系统所需的能源。尤其是训练 AI 模型可能消耗海量能源,这促使研究人员去寻找提升效率的方法,而不是一味扩大 AI 系统的规模和复杂度。一种可能的思路是,用专门的物理系统来承担其中一部分计算。

东京大学智能系统与信息学实验室的副教授 Kohei Nakajima 及其团队(其中包括 NTT 的研究人员)在最新的一系列实验中把两者结合起来,结果颇具前景。该研究发表在 Nature Computational Science 上。

用光来处理信息

“如今的 AI 系统已经具备惊人的能力,但它们也需要庞大的计算资源。与其继续打造更大、更复杂的模型,我们想重新思考学习过程本身,让物理系统能够更自然地完成计算,”研究生 Yongbo Zhang 说。“为此,我们转向了一种新兴的计算形式,用光而非电信号来处理信息。但要在这种形式上运行,我们还必须改变 AI 学习的工作方式,使它能够部署在与传统学习算法截然不同的硬件上。”

普通计算机芯片通过流经大量晶体管的电信号进行计算。这会消耗能量并产生热量。而光可以极快地传递信息,并且能同时承载多路信号。速度、并行处理能力与潜在能效的结合,使光计算成为 AI 应用中颇具前景的平台。传统 AI 方法可以在光学及其他物理系统上实现,但这样做在技术上颇具挑战,可能需要大量的测量、控制和数据存储。因此,研究人员探索能否重新设计学习过程,以更好地契合物理系统的特性。

更简单的训练,更少的测量

“我们提出了一种全新的整体思路,将名为 SS-DFA 的训练方法与一种更简单的网络架构——单映射框架(single-map framework)——结合起来,”Nakajima 说。

“传统训练需要在系统演化过程中测量并记录其信息,然后学习过程再回溯,以确定需要改变什么才能达到预期结果。我们的方法无需访问大多数这些中间状态,而是利用最终误差以及关于系统的信息来指导学习。这减少了所需的测量、数据存储和计算量。

“我们还设计了一种更简单的架构,其中众多单元遵循通用规则,而不是依赖一组高度复杂的内部连接。我们通过计算机仿真以及使用光计算系统开展的实验,验证了这一组合方法。”

令人意外的是,这种简化设计与更复杂的神经网络架构表现相当,并在部分测试中更胜一筹,而所需的计算量却少得多。在此前的研究中,团队展示了包括大语言模型在内的深度神经网络内部会自然涌现出复杂的活动模式,并提出这些模式可用于改进信息处理。这项新研究则证明,这些原理可以在光学系统中复现。

扩大规模并缩小到芯片上

未来的工作将探索该方法能否扩展到更大的 AI 模型、应用于涉及多种数据类型的更复杂任务,并在更广泛的算力平台上实现。如果成功,该框架有望在降低 AI 计算需求的同时,利用发热量很低的光学系统。这可能降低未来 AI 数据中心用于计算和冷却的能耗,同时由于热输出更低,还能减少用水量。

Nakajima 表示:“目前,我们已将所提出的架构集成到若干个相对基线的现代神经网络架构中,结果表明它能在减少计算量的同时提升性能。不过,我们尚未在当今最大的 AI 模型上测试它,尤其是语言模型和所谓的多模态模型,这是未来研究的一个重要方向。由于我们的框架是模块化的,可以作为计算模块插入现有网络,这为达到这样的规模提供了一条可能的路径。”

“而且,如果我们的系统能够实现小型化并集成到芯片上,它就能直接在手机、摄像头或自动驾驶汽车内部处理数据,从而实现更快的响应速度和更低的能耗。不过,在这一切变得切实可行之前,还需要在小型化、稳定性以及大规模制造方面开展进一步工作。”

Scalable physical deep learning using optical dynamics with state-skipping training and single-map architecture,Nature Computational Science(2026)。DOI: 10.1038/s43588-026-01075-w

期刊信息:Nature Computational Science

这篇报道的作者是谁?

英语硕士,自 2021 年起担任文字编辑,拥有高等教育与健康领域内容经验。致力于可信赖的科学新闻。完整简介 →

数学与生物学学士,创意写作硕士。游历广泛,对科学与语言有独到见解。完整简介 →

引用来源:要有光——新型 AI 框架运行于光学硬件之上(2026 年 11 月 5 日),2026 年 11 月 6 日检索自 https://techxplore.com/news/2026-11-ai-framework-optical-hardware.html

本文件受版权保护。除为私人学习或研究目的进行的任何合理使用外,未经书面许可,不得复制本文件的任何部分。内容仅供信息参考之用。

获取即时摘要文本(Gist)

在仿真和光学硬件实验中,将 SS-DFA 训练与单映射架构相结合,降低了测量、存储和计算需求。在一些测试中,该框架达到或超过了更复杂网络的水平,但尚未在最大的 AI 模型上测试。

本摘要由 LLM 自动生成。完整免责声明

译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。

查看英文原文(Let there be light—novel AI framework runs on optical hardware)

Let there be light—novel AI framework runs on optical hardware

Let there be light—novel AI framework runs on optical hardware

edited by Gaby Clark, reviewed by Robert Egan

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

peer-reviewed publication

Add to Preferred Sources

Let there be light – novel AI framework runs on optical hardware In the optical computing system used to demonstrate the single-map approach, information is converted into an optical signal, processed as it passes through a fiber loop, and then converted back into an electrical signal for analysis. The system uses a 200-meter optical fiber and a small number of electronic components to perform the AI calculations. Credit: 2026 Nakajima et al. CC-BY-ND

Artificial intelligence is increasingly pervasive and capable but is also very hungry for power. Researchers, including those at the University of Tokyo, have developed a new approach to building physics-based AI—systems that use the natural behavior of physical systems to process information—that dramatically reduces the amount of computation required for them to run. The approach simplifies both how these systems learn and how they are structured. It was demonstrated using an optical computing system that processes information with light and could help pave the way toward faster and more energy-efficient AI hardware.

It's hard to ignore the presence of AI. News stories and software constantly make its presence felt, even if you don't interact with AI systems directly. Behind the scenes, AI systems are becoming larger, more complicated and more resource-intensive. One of the biggest concerns around the growth of AI is the energy required to run these systems. Training AI models in particular can consume vast amounts of energy, driving researchers to search for ways to improve efficiency rather than simply increasing the size and complexity of AI systems. One possible approach is to use specialized physical systems to perform some of the calculations.

Associate professor Kohei Nakajima from the Laboratory for Intelligent Systems and Informatics at the University of Tokyo and his team, including NTT researchers, combined both in their latest set of experiments, and the results are promising. The study is published in Nature Computational Science.

Using light to process information

"Today's AI systems have achieved remarkable capabilities, but they also require enormous computational resources. Instead of continuing to build larger and more complicated models, we wanted to rethink the learning process itself so that physical systems can perform computation much more naturally," said graduate student Yongbo Zhang. "For this, we turned toward an emerging form of computation that uses light to process information instead of electrical signals. But to operate with this, we also had to change the way AI learning works so it could be implemented on vastly different hardware from traditional learning algorithms."

Ordinary computer chips perform calculations using electrical signals that run through large numbers of transistors. This consumes energy and produces heat. Light, however, can carry information extremely quickly and can carry multiple signals simultaneously. This combination of speed, parallel processing and potential energy efficiency makes optical computing a promising platform for AI applications. Conventional AI methods can be implemented on optical and other physical systems, but doing so can be technically challenging and may require considerable measurement, control and data storage. The researchers therefore explored whether the learning process could be redesigned to better suit the characteristics of physical systems.

Simpler training with fewer measurements

"We developed a new overall approach combining a training method called SS-DFA with a simpler network architecture called the single-map framework," said Nakajima.

"Conventional training requires information about the system to be measured and recorded as it evolves, before the learning process can then backtrack to determine what needs to change to achieve a desired outcome. Our method avoids the need to access most of these intermediate states, using the final error together with information about the system to guide learning. This reduces the amount of measurement, data storage and computation required.

"We also designed a simpler architecture in which many units follow the general rules, rather than relying on a set of highly complex internal connections. We demonstrated the combined approach through computer simulations and experiments using an optical computing system."

Surprisingly, the simplified design matched, and in some tests outperformed, more complex neural network architectures, while requiring far less computation. In previous research, the team showed complex patterns of activity naturally emerged inside deep neural networks, including large language models, and suggested these patterns could be used to improve information processing. The new study demonstrated that these principles can be reproduced in an optical system.

Scaling up and shrinking onto chips

Future work will explore whether the approach can be scaled to larger AI models, applied to more complex tasks involving multiple types of data, and implemented on a wider range of computing platforms. If successful, the framework could reduce the computational demands of AI while taking advantage of optical systems that generate little heat. This could lower the energy needed for both computing and cooling in future AI data centers, while also reducing water consumption due to the lower heat output.

"At present, we have integrated the proposed architecture into several relatively baseline modern neural network architectures, and the results show that it can improve performance while reducing computation," said Nakajima. "However, we have not yet tested it on today's largest AI models, particularly language and so-called multimodal models, and this is an important direction for future research. Because our framework is modular and can be inserted as a computational block into existing networks, it provides a possible route toward such scales.

"And, if our system can be miniaturized and integrated onto a chip, it could process data directly inside phones, cameras or self-driving cars, enabling faster responses with lower energy consumption. Before this becomes practical, however, further work is needed on miniaturization, stability and large-scale manufacturing."

Scalable physical deep learning using optical dynamics with state-skipping training and single-map architecture, Nature Computational Science (2026). DOI: 10.1038/s43588-026-01075-w

Journal information:Nature Computational Science

Who's behind this story?

Gaby Clark

MA in English, copy editor since 2021 with experience in higher education and health content. Dedicated to trustworthy science news. Full profile →

Bachelor's in mathematical biology, Master's in creative writing. Well-traveled with unique perspectives on science and language. Full profile →

Citation: Let there be light—novel AI framework runs on optical hardware (2026, November 5) retrieved 6 November 2026 from https://techxplore.com/news/2026-11-ai-framework-optical-hardware.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Get Instant Summarized Text (Gist)

Combining SS-DFA training with a single-map architecture reduced measurement, storage and computation needs in simulations and optical hardware experiments. The framework matched or exceeded more complex networks in some tests, but remains untested on the largest AI models.

This summary was automatically generated using LLM. Full disclaimer

This site uses cookies to assist with navigation, analyse your use of our services, collect data for ads personalisation and provide content from third parties. By using our site, you acknowledge that you have read and understand our Privacy Policy and Terms of Use.

原文为英文,正文由自动抓取并保留原文。

本文由采集器自动同步

原文发布于 TechXplore(Let there be light—novel AI framework runs on optical hardware),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。

阅读原文 ↗