arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.08317cond-mat.softcond-mat.dis-nncond-mat.stat-mech
收藏

机械网络的学习多稳定性

Learned multi-stability in mechanical networks

Menachem Stern, Matthew B. Pinson, Arvind Murugan

摘要:

我们对比了材料设计和物理学习的不同框架,以创建具有所需稳定状态的弹性网络。在设计中,预先指定所需的状态,并且可以利用这些知识在计算机上优化材料参数。在学习过程中,材料在物理上依次经历所需的稳定状态,改变材料以稳定每个额外的状态。我们发现,虽然设计的状态是稳定的线性虎克弹簧网络,顺序学习需要特定的非线性弹性。我们发现,这种非线性稳定状态,其中应变为零,在一些弹簧和大的其他,从而发挥作用的贝叶斯先验稀疏统计回归。我们的模型展示了特定的材料属性如何通过材料本身的部署来持续学习新功能。

英文摘要:

We contrast the distinct frameworks of materials design and physical learning in creating elastic networks with desired stable states. In design, the desired states are specified in advance and material parameters can be optimized on a computer with this knowledge. In learning, the material physically experiences the desired stable states in sequence, changing the material so as to stabilize each additional state. We show that while designed states are stable in networks of linear Hookean springs, sequential learning requires specific non-linear elasticity. We find that such non-linearity stabilizes states in which strain is zero in some springs and large in others, thus playing the role of Bayesian priors used in sparse statistical regression. Our model shows how specific material properties allow continuous learning of new functions through deployment of the material itself.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑