光计算
Search documents
中国科学院高精度光计算研究取得进展
Huan Qiu Wang Zi Xun· 2026-01-11 04:13
来源:环球网 【环球网科技综合报道】1月11日消息,据《先进光子学》(Advanced Photonics)报道,在人工智能神 经网络高速发展的背景下,大规模的矩阵运算与频繁的数据迭代给传统电子处理器带来了巨大压力。光 电混合计算通过光学处理与电学处理的协同集成,展现出显著的计算性能,然而实际应用受限于训练与 推理环节分离、离线权重更新等问题,造成信息熵劣化、计算精度下降,导致推理准确度低。 中国科学院半导体研究所提出了一种基于相位像素阵列的可编程光学处理单元(OPU),并结合李雅普 诺夫稳定性理论实现了对OPU的灵活编程。在此基础上,团队构建了一种端到端闭环光电混合计算架构 (ECA),通过硬件—算法协同设计,实现了训练与推理的全流程闭环优化,有效补偿了信息熵损失, 打破了光计算中计算精度与准确度之间的强耦合关系。 该架构通过噪声自学习机制,实现了光学与电学参数联合优化与自适应计算精度补偿。实验结果表明, 采用4-bit的OPU时,ECA在MNIST手写数字识别任务(计算机视觉领域的经典任务)上的推理准确率达 到90.8%,接近8-bit传统计算架构(TCA)的理论极限(90.9%),这表明光计算系统在低硬 ...
2025国际十大科技新闻解读
Ke Ji Ri Bao· 2025-12-25 01:00
2025年,人类在探索未知的征程中留下了坚实的足迹。从"深度求索"用算法点亮AI效率革命,到谷 歌量子计算首次实现可验证的算力超越;从鲁宾天文台以巨眸凝视宇宙起源,到跨物种脑图谱揭开神经 发育的奥秘……科技的力量既指向星辰大海,也照进生命精微深处。 在本报评选的十大国际科技新闻展示的图景中,有深沉的警醒,也有科技的温度:首个气候临界点 的到达警示着气候的脆弱,脑科学与手术机器人的突破则承载着对个体健康的深切关怀。科技的真谛, 从来不仅是追求极致,更是守护共生,是智慧与责任同行。我们相信,科技的内核永远是温暖的,引领 人类走向更坚韧、更包容的未来。 "深度求索"引领开源人工智能模式 在人工智能(AI)浪潮奔涌的2025年伊始,中国"深度求索"(DeepSeek)公司以其开源大模型 DeepSeek-R1的突破性成果,在世界AI发展史上留下了深刻印记。 DeepSeek-R1开创性地采用纯强化学习训练大规模推理模型,在提升模型能力的同时,显著降低了 对标注数据的依赖。该团队今年9月在《自然》杂志发表的论文,系统阐述了这一技术路径的科学价值 与工程实现。其实现了在有限算力条件下达到顶尖性能的目标,展现了中国科研人员 ...
DeepSeek-OCR实现光学压缩 光计算可为大模型“减负”
3 6 Ke· 2025-11-27 08:49
Group 1 - The core idea of the article revolves around the concept of optical compression of context using visual tokens to address the computational challenges faced by large language models as context window sizes increase [2][3] - DeepSeek's research demonstrates that visual compression can maintain high accuracy, achieving a compression rate of 10 times while retaining 96.5% precision [3][4] - The DeepEncoder module is identified as the key engine for achieving optical compression, utilizing components such as the SAM module, convolutional blocks, and CLIP to effectively compress data from 1000 text tokens to 100 visual tokens [5][7] Group 2 - Optical computing is highlighted as a more suitable solution for context compression due to its ability to handle the information aggregation processes inherent in ViT and CNN structures more efficiently than traditional electronic chips [7][9] - The advantages of optical computing include simplified computation processes and scalability, allowing for enhanced parallelism and dynamic programmability, which are crucial for long text reasoning tasks [9][11] - Future plans involve exploring algorithms based on human memory mechanisms and developing specialized hardware for context compression and AI tasks, aiming to connect optical computing with large models [13][15] Group 3 - The article emphasizes the need for optical computing to overcome the limitations of traditional GPUs, particularly in terms of memory constraints and power density, as large models become more prevalent [15] - The company aims to build a next-generation disruptive platform system for large-scale AI computing, providing comprehensive optical computing solutions across various scenarios [15]