Scaling Up Thermodynamic AI Models 文章

ArXiv CS.AI2026-07-02PAPERen作者: Andrew G. Moore

详细信息

来源站点
ArXiv CS.AI
作者
Andrew G. Moore
文章类型
PAPER
语言
en
发布日期
2026-07-02

摘要

arXiv:2607.00170v1 Announce Type: cross Abstract: Thermodynamic computing devices based on the Ising model show great promise for low-power AI inference and edge computing, but scalable methods for training large models for such hardware remain limited. Prior theory shows that the time-averaged behavior of high-temperature Gibbs-sampled Ising systems can implement feed-forward neural inference. We turn this theoretical correspondence into a scalable and purely backpropagation-based algorithm for training deep convolutional networks for thermodynamic inference on Ising machine hardware. Our image classification models achieve accuracies of 94.9% on CIFAR-10 and 76.0% on CIFAR-100 under binary Gibbs sampling. We then develop and experimentally validate a mathematical theory relating inference cost to accuracy and controlling autocorrelation times.