PulseAugur
中
实时 08:23:57
English(EN) In Situ Training of Optical Neural Networks by Coding Agents

编码代理使用“代码即光学”方法训练光学神经网络

研究人员开发了一种名为“代码即光学”的新颖方法,该方法利用由大型语言模型驱动的编码代理,直接从硬件测量中训练光学神经网络。这种方法绕过了对每个设备进行校准或复杂梯度计算的需要,而是允许代理学习光学系统的物理特性并优化其参数。与传统的无梯度技术相比,该方法在分类和图像编码任务中表现出优越的性能,为开发光学神经网络提供了更具成本效益和可扩展性的途径。 AI

影响 这项研究通过实现更易于访问和可扩展的光学神经网络训练,有可能加速节能光学计算的发展。

排序理由 该项目描述了学术论文中提出的一种训练光学神经网络的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

编码代理使用“代码即光学”方法训练光学神经网络

本文如何被排名

Signal score
22 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该项目描述了学术论文中提出的一种训练光学神经网络的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Ilker Oguz, Colin Christian, Christophe Moser, Demetri Psaltis, Gordon Wetzstein ·

    通过编码代理进行光学神经网络的原位训练

    arXiv:2611.23875v1 Announce Type: cross Abstract: Optical neural networks promise fast, energy-efficient computing, but every device departs from its design and must be trained with the hardware. In situ training relies on an expert-built calibrated digital model of each device o…