High-Speed CMOS-Free Purely Spintronic Asynchronous Recurrent Neural Network
High-Speed CMOS-Free Purely Spintronic Asynchronous Recurrent Neural Network
复制标题
高速无cmos的纯自旋电子异步递归神经网络
DOI：
10.1063/5.0129006
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Pranav O. Mathews;Christian B. Duffee;Abel Thayil;Ty E. Stovall;C. Bennett;F. García-Sánchez;M. Marinella;J. Incorvia;Naimul Hassan;Xuan Hu;J. Friedman
中科院分区：
文献类型：
--
作者：
Pranav O. Mathews;Christian B. Duffee;Abel Thayil;Ty E. Stovall;C. Bennett;F. García-Sánchez;M. Marinella;J. Incorvia;Naimul Hassan;Xuan Hu;J. Friedman
人类大脑的特殊能力为人工智能硬件提供了灵感，这些硬件模仿了神经生物学的功能和结构。特别是，最近开发的纳米器件与仿生特性的承诺，使神经形态架构的发展具有卓越的计算效率。在这项工作中，我们提出了由畴壁磁性隧道结组成的仿生神经元，可以集成到第一个具有仿生组件的可训练无CMOS递归神经网络中。本文证明了该系统的基准任务的计算效率和上级计算效率相对于替代方法的递归神经网络。
The exceptional capabilities of the human brain provide inspiration for artificially intelligent hardware that mimics both the function and the structure of neurobiology. In particular, the recent development of nanodevices with biomimetic characteristics promises to enable the development of neuromorphic architectures with exceptional computational efficiency. In this work, we propose biomimetic neurons comprised of domain wall-magnetic tunnel junctions that can be integrated into the first trainable CMOS-free recurrent neural network with biomimetic components. This paper demonstrates the computational effectiveness of this system for benchmark tasks and its superior computational efficiency relative to alternative approaches for recurrent neural networks.