CMOS + 随机纳米磁体：概率推理和学习的异质计算机（英文版）

英文标题：CMOS + stochastic nanomagnets: heterogeneous computers for probabilistic inference and learning中文摘要：本文提出了一种异构计算器，该计算器将基于随机磁隧道结的概率位（p-bits）与现有的 CMOS 技术相结合，恰当的设计提高了概率计算的能效，提供了比仿真高质量的随机比特。英文摘要：With the slowing down of Moore's law, augmenting complementary-metal-oxidesemiconductor (CMOS) transistors with emerging nanotechnologies (X) is becomingincreasingly important. In this paper, we demonstrate how stochastic magnetictunnel junction (sMTJ)-based probabilistic bits, or p-bits, can be combine