当前位置: X-MOL 学术Phys. Rev. X › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Supervised Learning in Physical Networks: From Machine Learning to Learning Machines
Physical Review X ( IF 12.5 ) Pub Date : 2021-05-28 , DOI: 10.1103/physrevx.11.021045
Menachem Stern , Daniel Hexner , Jason W. Rocks , Andrea J. Liu

Materials and machines are often designed with particular goals in mind, so that they exhibit desired responses to given forces or constraints. Here we explore an alternative approach, namely physical coupled learning. In this paradigm, the system is not initially designed to accomplish a task, but physically adapts to applied forces to develop the ability to perform the task. Crucially, we require coupled learning to be facilitated by physically plausible learning rules, meaning that learning requires only local responses and no explicit information about the desired functionality. We show that such local learning rules can be derived for any physical network, whether in equilibrium or in steady state, with specific focus on two particular systems, namely disordered flow networks and elastic networks. By applying and adapting advances of statistical learning theory to the physical world, we demonstrate the plausibility of new classes of smart metamaterials capable of adapting to users’ needs in situ.

中文翻译:

物理网络中的监督学习:从机器学习到学习机器

材料和机器的设计通常考虑到特定的目标,以便它们对给定的力或约束表现出所需的响应。在这里,我们探索另一种方法,即物理耦合学习. 在这种范式中,系统最初并不是为完成任务而设计的,而是在物理上适应所施加的力以培养执行任务的能力。至关重要的是,我们需要通过物理上合理的学习规则来促进耦合学习,这意味着学习只需要本地响应,不需要有关所需功能的明确信息。我们表明,可以为任何物理网络推导出这种局部学习规则,无论是处于平衡状态还是稳态,特别关注两个特定系统,即无序流网络和弹性网络。通过将统计学习理论的进步应用和适应物理世界,我们证明了能够在原位适应用户需求的新型智能超材料的合理性。
更新日期:2021-05-28
down
wechat
bug