Magnetic Tunnel Junction Enabled Stochastic Spiking Neural Networks: From Non-Telegraphic to Telegraphic Switching Regime
Magnetic Tunnel Junction Enabled Stochastic Spiking Neural Networks: From Non-Telegraphic to Telegraphic Switching Regime
复制标题
DOI：
10.1103/physrevapplied.8.064017
复制
发表时间：
2017-09
期刊：
影响因子：
--
通讯作者：
C. Liyanagedera;Abhronil Sengupta;Akhilesh R. Jaiswal;K. Roy
中科院分区：
文献类型：
--
作者：
C. Liyanagedera;Abhronil Sengupta;Akhilesh R. Jaiswal;K. Roy
基于纳米电子自旋装置的随机脉冲神经网络可能是实现“类脑”紧凑节能认知智能的一种可能途径。该计算模型试图利用纳米电子突触或神经组件的固有设备随机性来执行学习或推理。然而，对于随机自旋装置的标度效应及其对随机网络运行的影响，在系统层面的分析很少。本研究尝试探索基于纳米磁体的随机神经形态计算架构的设计空间，并分析其在不同势垒高度磁体下的性能。我们说明了底层网络架构必须如何修改，以解释低势垒高度磁铁在缩放到超顺磁状态时所显示的随机电报切换行为。针对MNIST数据集上的数字识别问题，我们对深度神经网络架构进行了设备到系统级的分析。
Stochastic Spiking Neural Networks based on nanoelectronic spin devices can be a possible pathway at achieving"brain-like"compact and energy-efficient cognitive intelligence. The computational model attempt to exploit the intrinsic device stochasticity of nanoelectronic synaptic or neural components to perform learning or inference. However, there has been limited analysis on the scaling effect of stochastic spin devices and its impact on the operation of such stochastic networks at the system level. This work attempts to explore the design space and analyze the performance of nano-magnet based stochastic neuromorphic computing architectures for magnets with different barrier heights. We illustrate how the underlying network architecture must be modified to account for the random telegraphic switching behavior displayed by magnets with low barrier heights as they are scaled into the superparamagnetic regime. We perform a device to system level analysis on a deep neural network architecture for a digit recognition problem on the MNIST dataset.