Scholarlink

<p>Physical neural networks (PNNs) are neural-like computational frameworks that exploit the intrinsic dynamics of physical media to achieve ultrafast and energy-efficient information processing. However, the complex and strongly-coupled physical nature of PNNs in disordered environments makes them resistant to accurate differentiable modeling. Here, we propose a concept of <i>computational space</i> that empowers the chaotic environment itself with computational capabilities. This space constitutes a large-scale, model-agnostic PNN through distributed intelligent metasurfaces. To enable effective training, we develop a fully-forward learning framework that estimates zeroth-order gradients from in-situ measurable electromagnetic feedback, thereby circumventing the rigorous modeling requirements of conventional backpropagation. In experiments, we construct such computational space that achieves recognition accuracies of 97% for alphabetic characters and 99% for numeric patterns. Furthermore, the space exhibits the functionalities of enhanced focusing under disordered scattering conditions and reliable human position localization. This emerging paradigm of self-evolving physical intelligence holds potential for advancing embodied intelligence, autonomous cyber–physical systems, and next-generation human–machine interaction, marking a fundamental transition from <i>computing the physics</i> to <i>computing with physics</i>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Creation of a computational space with model-free metasurface neural network

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月20日

查看全文
  • Mingfei Song,
  • Chao Qian,
  • Gaoang Wang,
  • Cheng Li,
  • Fang Yuan,
  • Ali Momeni,
  • Romain Fleury,
  • Hongsheng Chen

摘要

Physical neural networks (PNNs) are neural-like computational frameworks that exploit the intrinsic dynamics of physical media to achieve ultrafast and energy-efficient information processing. However, the complex and strongly-coupled physical nature of PNNs in disordered environments makes them resistant to accurate differentiable modeling. Here, we propose a concept of computational space that empowers the chaotic environment itself with computational capabilities. This space constitutes a large-scale, model-agnostic PNN through distributed intelligent metasurfaces. To enable effective training, we develop a fully-forward learning framework that estimates zeroth-order gradients from in-situ measurable electromagnetic feedback, thereby circumventing the rigorous modeling requirements of conventional backpropagation. In experiments, we construct such computational space that achieves recognition accuracies of 97% for alphabetic characters and 99% for numeric patterns. Furthermore, the space exhibits the functionalities of enhanced focusing under disordered scattering conditions and reliable human position localization. This emerging paradigm of self-evolving physical intelligence holds potential for advancing embodied intelligence, autonomous cyber–physical systems, and next-generation human–machine interaction, marking a fundamental transition from computing the physics to computing with physics.