arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.15416cond-mat.stat-mechcs.LGmath.DSnlin.AOstat.ML
收藏

通过最大化工作生产的热力学机器学习

Thermodynamic Machine Learning through Maximum Work Production

Complexity Institute, Nanyang Technological University(南洋理工大学复杂系统研究所);School of Physical and Mathematical Sciences, Nanyang Technological University(南洋理工大学物理与数学科学学院);Complexity Sciences Center and Physics Department, University of California at Davis(加州大学戴维斯分校复杂科学中心与物理系);Centre for Quantum Technologies, National University of Singapore(新加坡国立大学量子技术中心)

A. B. Boyd, J. P. Crutchfield, M. Gu

摘要:

适应系统--如获得生存优势的生物有机体、执行功能任务的自主机器人或运输细胞内营养物质的运动蛋白--必须模拟其环境中的随机性和随机性,以充分利用热力学资源。类似地,但在纯粹的计算领域,机器学习算法估计模型以捕获可预测的结构并识别训练数据中不相关的噪声。这是通过优化性能指标(如模型可能性)来实现的。如果物理实现,通过机器学习估计的计算模型在物理上是否更受欢迎?我们介绍了热力学原理,即工作生产是自适应物理代理最相关的性能指标,并将结果与指导机器学习的最大似然原理进行比较。在类的物理代理,最有效地收获能源从他们的环境中,我们证明了一个有效的代理的模型明确地确定其架构和有多少有用的工作,它从环境中收获。然后,我们表明,选择最大的工作代理给定的环境数据对应于找到最大似然模型。这建立了非平衡态热力学和动态学习之间的等价关系。通过这种方式,工作最大化成为自适应热力学系统学习的组织原则。

英文摘要:

Adaptive systems -- such as a biological organism gaining survival advantage, an autonomous robot executing a functional task, or a motor protein transporting intracellular nutrients -- must model the regularities and stochasticity in their environments to take full advantage of thermodynamic resources. Analogously, but in a purely computational realm, machine learning algorithms estimate models to capture predictable structure and identify irrelevant noise in training data. This happens through optimization of performance metrics, such as model likelihood. If physically implemented, is there a sense in which computational models estimated through machine learning are physically preferred? We introduce the thermodynamic principle that work production is the most relevant performance metric for an adaptive physical agent and compare the results to the maximum-likelihood principle that guides machine learning. Within the class of physical agents that most efficiently harvest energy from their environment, we demonstrate that an efficient agent's model explicitly determines its architecture and how much useful work it harvests from the environment. We then show that selecting the maximum-work agent for given environmental data corresponds to finding the maximum-likelihood model. This establishes an equivalence between nonequilibrium thermodynamics and dynamic learning. In this way, work maximization emerges as an organizing principle that underlies learning in adaptive thermodynamic systems.

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。

↑