Supervised learning through physical changes in a mechanical system
Supervised learning through physical changes in a mechanical system
复制标题
通过机械系统中的物理变化进行监督学习
DOI：
10.1073/pnas.2000807117
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
A. Murugan
中科院分区：
文献类型：
--
作者：
M. Stern;Chukwunonso Arinze;Leron Perez;S. Palmer;A. Murugan
重要性监督学习算法可以学习将一类输入示例与另一类输入示例区分开的细微特征。我们探索了一个监督训练框架，在这个框架中，机械超材料通过利用材料中的可塑性和非线性来学习区分不同类别的力。经过一段时间的力量训练，材料可以正确地响应以前看不见的新力量，这些力量与训练示例共享空间相关模式。这种泛化可以允许微电子和自适应机器人的机械部件学习区分飞行中的力刺激模式。我们的工作表明，学习和泛化并不局限于软件算法，而是可以自然地从弹性材料的塑性和非线性中产生。机械超材料通常被设计为对规定的力显示期望的响应。在某些应用中，所需的力-响应关系很难精确指定，但力和所需响应的示例很容易获得。在这里，我们提出了一个监督学习的框架，在薄的，有折痕的床单，学习所需的力响应行为，通过物理体验训练的例子，然后，至关重要的是，正确的反应（概括）以前看不见的测试力量。在训练过程中，我们使用训练力折叠纸张，促使局部折痕刚度与其经历的应变成比例变化。我们发现，这个学习过程重塑折叠片材固有的非线性，以显示正确的反应，以前看不见的测试力。我们展示了学习表中的训练误差、测试误差和表大小（模型复杂度）之间的关系，并将其与机器学习算法中的对应物进行了比较。我们的框架展示了如何通过局部物理学习过程来塑造无序机械材料的崎岖能量景观，以显示所需的力响应行为。
Significance Supervised learning algorithms can learn subtle features that distinguish one class of input examples from another. We explore a supervised training framework in which mechanical metamaterials physically learn to distinguish different classes of forces by exploiting plasticity and nonlinearities in the material. After a period of training with examples of forces, the material can respond correctly to previously unseen novel forces that share spatial correlation patterns with the training examples. Such generalization can allow mechanical parts of microelectronics and adaptive robotics to learn to distinguish patterns of force stimuli on the fly. Our work shows how learning and generalization are not restricted to software algorithms, but can naturally emerge from plasticity and nonlinearities in elastic materials. Mechanical metamaterials are usually designed to show desired responses to prescribed forces. In some applications, the desired force–response relationship is hard to specify exactly, but examples of forces and desired responses are easily available. Here, we propose a framework for supervised learning in thin, creased sheets that learn the desired force–response behavior by physically experiencing training examples and then, crucially, respond correctly (generalize) to previously unseen test forces. During training, we fold the sheet using training forces, prompting local crease stiffnesses to change in proportion to their experienced strain. We find that this learning process reshapes nonlinearities inherent in folding a sheet so as to show the correct response for previously unseen test forces. We show the relationship between training error, test error, and sheet size (model complexity) in learning sheets and compare them to counterparts in machine-learning algorithms. Our framework shows how the rugged energy landscape of disordered mechanical materials can be sculpted to show desired force–response behaviors by a local physical learning process.
影响因子：
29.4
作者：
Kang, Ji-Hwan;Kim, Hyunki;Hayward, Ryan C.
通讯作者：
Hayward, Ryan C.