arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.03623cond-mat.stat-mechcond-mat.dis-nnphysics.bio-ph
收藏

用表征学习量化远离平衡的多体学习

Quantifying many-body learning far from equilibrium with representation learning

Weishun Zhong, Jacob M. Gold, Sarah Marzen, Jeremy L. England, Nicole Yunger Halpern

摘要:

远离平衡的多体系统,从肥皂泡到悬浮液再到聚合物,学习推动它们的驱动力。这种学习已经通过热力学性质观察到,例如功吸收和应变。我们超越了最初为平衡环境定义的这些宏观属性:我们用机器学习量化统计机械学习。我们的工具包依赖于我们在远离平衡的统计力学和表示学习之间识别的结构平行,这是由包含瓶颈的神经网络(包括变分自编码器)所经历的。我们训练一个变分自动编码器,通过无监督学习,在强驾驶过程中的多体系统假设的配置。我们分析了神经网络的瓶颈,以衡量多体系统的分类能力,记忆能力,辨别能力,和新颖性检测。自旋玻璃的数值模拟说明了我们的技术。该工具包揭示了逃避热力学测量检测的自组织,更可靠,更精确地识别和量化物质学习。

英文摘要:

Far-from-equilibrium many-body systems, from soap bubbles to suspensions to polymers, learn the drives that push them. This learning has been observed via thermodynamic properties, such as work absorption and strain. We move beyond these macroscopic properties that were first defined for equilibrium contexts: We quantify statistical mechanical learning with machine learning. Our toolkit relies on a structural parallel that we identify between far-from-equilibrium statistical mechanics and representation learning, which is undergone by neural networks that contain bottlenecks, including variational autoencoders. We train a variational autoencoder, via unsupervised learning, on configurations assumed by a many-body system during strong driving. We analyze the neural network's bottleneck to measure the many-body system's classification ability, memory capacity, discrimination ability, and novelty detection. Numerical simulations of a spin glass illustrate our technique. This toolkit exposes self-organization that eludes detection by thermodynamic measures, more reliably and more precisely identifying and quantifying learning by matter.

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。

↑