Learning Without Neurons in Physical Systems
Learning Without Neurons in Physical Systems
复制标题
DOI：
10.1146/annurev-conmatphys-040821-113439
复制
发表时间：
2022-06
影响因子：
22.6
通讯作者：
M. Stern;A. Murugan
中科院分区：
文献类型：
--
作者：
M. Stern;A. Murugan
学习传统上是在生物或计算系统中研究的。学习框架在解决硬逆问题中的力量为物理学习的发展提供了一个有吸引力的案例，其中物理系统在没有计算设计的情况下自行采用所需的属性。最近人们意识到，大类的物理系统可以通过本地学习规则进行物理学习，根据观察到的使用示例自主调整参数。我们回顾了物理学习这一新兴领域的最新工作，描述了从分子自组装到流动网络和机械材料等领域的理论和实验进展。物理学习机器相对于计算机设计的机器提供了多种实际优势，特别是不需要系统的精确模型，以及它们随着时间的推移自主适应不断变化的需求的能力。物理学习机作为一种理论构造，为物理约束如何修正抽象学习理论提供了一个新的视角。
Learning is traditionally studied in biological or computational systems. The power of learning frameworks in solving hard inverse problems provides an appealing case for the development of physical learning in which physical systems adopt desirable properties on their own without computational design. It was recently realized that large classes of physical systems can physically learn through local learning rules, autonomously adapting their parameters in response to observed examples of use. We review recent work in the emerging field of physical learning, describing theoretical and experimental advances in areas ranging from molecular self-assembly to flow networks and mechanical materials. Physical learning machines provide multiple practical advantages over computer designed ones, in particular by not requiring an accurate model of the system, and their ability to autonomously adapt to changing needs over time. As theoretical constructs, physical learning machines afford a novel perspective on how physical constraints modify abstract learning theory.