热力学学习
Thermodynamic learning
浏览论文内容
中文总结 AI 辅助
该研究提出一种基于热力学系统的学习方法，以伊辛系统为实例，证明小型热力学系统即可具备出色记忆与良好泛化能力，且性能随系统规模提升。
中文摘要 AI 辅助
我们探讨训练热力学系统的可能性，该系统的微观变量通过哈密顿量依据常规统计力学规则完全确定，可执行记忆与泛化等任务。训练通过施加合适的外场实现，外场起到“数据”的作用。与传统机器学习不同，未引入其他逻辑或算法规则。该系统原则上可进行精确解析计算。我们将此通用方法应用于具有退火二分耦合的原型伊辛（Ising）系统，研究其学习能力。结果表明，小型系统已具备出色的记忆能力和良好的泛化能力，且性能随系统规模增大呈提升趋势。
英文摘要
We discuss the possibility to train a thermodynamic system, whose micro-variables are fully determined through the Hamiltonian by the usual statistical mechanical rules, to perform tasks such as memorization and generalization. Training is achieved by the application of suitable external fields, playing the role of {\it data}. At variance with conventional machine learning, no other logical or algorithmic rules are introduced. The system is amenable, in principle, to exact analytical calculations. We specialize this general approach to a prototypical Ising system with annealed dichotomous couplings and study its learning ability. Results indicate excellent memorization and good generalization capacity already for small systems, and a tendency to improve with system size.
发表机构
- Dipartimento di Fisica “E. R. Caianiello” and INFN, Gruppo Collegato di Salerno（萨莱诺联合小组 E.R.卡亚涅洛物理系及意大利国家核物理研究所）
机构由 AI 辅助整理，请以论文原文为准。
