发表机构
University of Michigan（密歇根大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种动态网络材料的原位局部学习框架，通过正向与时间反转伴随误差驱动计算梯度，实现弹簧常数等参数训练，并编程多种动态功能，使材料兼具可编程物质与物理神经网络特性。
AI 中文摘要
功能材料通过预先设计的结构实现功能，而物理神经网络则通过规定输入输出行为进行训练。将这两种观点统一起来，将使材料能够直接从动态任务中获取功能。在此，我们提出一种用于动态网络材料的原位局部学习框架。将正向驱动和经过时间反转的伴随误差驱动施加到同一力学网络上，使材料能够通过自身动力学计算时域损失的梯度。由此产生的更新规则是局部的，符合物理学习的原则。每个键或节点仅需共位的正向场和伴随场。该方法训练弹簧常数、节点质量、键阻尼系数和节点阻尼系数，并编程实现动态功能，包括宽带波隐身、倏逝波成像、被动瞬态输出增强和元音分类。这些示例涉及不同的物理机制，如波散射、近场信息传递、耗散非正态动力学和机器学习，但仅通过改变损失函数即可获得，而无需利用专家知识。因此，动态网络材料既可以作为可编程物质，也可以作为物理神经网络，为材料系统原位学习时间响应提供了一条途径。
英文摘要
Functional materials realize functionalities through pre-designed structures, whereas physical neural networks are trained by prescribing input-output behavior. Unifying these views would allow materials to acquire functions directly from dynamical tasks. Here we introduce an in situ local learning framework for dynamic network materials. A forward drive and a time-reversed adjoint error drive are applied to the same mechanical network, enabling the material to compute gradients of a time-domain loss through its own dynamics. The resulting update rules are local, compatible with the principle of physical learning. Each bond or node requires only co-located forward and adjoint fields. The method trains spring constants, nodal masses, bond damping coefficients and nodal damping coefficients, and programs dynamical functions including broadband wave cloaking, evanescent-wave imaging, passive transient output enhancement and vowel classification. These examples involve distinct physical mechanisms, such as wave scattering, near-field information transfer, dissipative non-normal dynamics and machine learning, but are obtained by simply changing the loss function, rather than leveraging expert knowledge. Therefore, dynamic network materials can act both as programmable matter and as physical neural networks, providing a route to material systems that learn temporal responses in situ.
Comments26 pages, 5 figures
