将伊辛机与神经网络对应，实现高温下神经网络在伊辛硬件上运行
Correspondence Between Ising Machines and Neural Networks
- 用自旋平均替代基态，支持高温计算
- 建立伊辛机与前馈神经网络的系统映射关系
- 证明该方法在所有情况下都能成功实现
基于伊辛模型的计算是未来计算技术（如量子退火、绝热量子计算和热力学经典计算）的核心。传统方法将计算结果等同于基态，本文将其推广至自旋平均，使计算可在高温条件下进行。随后提出伊辛设备与神经网络之间的系统性对应关系，并给出一种简单方法，可将训练好的前馈神经网络部署到伊辛型硬件上。最后，提供了数学证明，表明此类实现始终有效。
原文摘要 · Abstract (English)
Computation with the Ising model is central to future computing technologies like quantum annealing, adiabatic quantum computing, and thermodynamic classical computing. Traditionally, computed values have been equated with ground states. This paper generalizes computation with ground states to computation with spin averages, allowing computations to take place at high temperatures. It then introduces a systematic correspondence between Ising devices and neural networks and a simple method to run trained feed-forward neural networks on Ising-type hardware. Finally, a mathematical proof is offered that these implementations are always successful.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。