Probabilistic Deep Spiking Neural Systems Enabled by Magnetic Tunnel Junction
Probabilistic Deep Spiking Neural Systems Enabled by Magnetic Tunnel Junction
复制标题
DOI：
10.1109/ted.2016.2568762
复制
发表时间：
2016-07-01
影响因子：
3.1
通讯作者：
Roy, Kaushik
中科院分区：
文献类型：
--
作者：
Sengupta, Abhronil;Parsa, Maryam;Roy, Kaushik
深度脉冲神经网络正在成为认知计算平台日益强大的工具。然而，大多数关于此类计算模型的现有研究都是在对底层硬件实现的了解有限的情况下开发的，从而导致面积和功耗昂贵的设计。虽然最近已经提出了几种模拟神经操作的神经模拟装置，但它们的功能仅限于非常简单的神经模型，在复杂的识别任务中可能被证明效率低下。在本文中，我们冒险进入相对未开发的领域，利用这种神经模拟装置的固有设备随机性在时域的概率框架中模拟复杂的神经功能。我们考虑实现一个能够执行高精度和低延迟分类任务的深度尖峰神经网络，其中神经计算单元由磁隧道结的随机切换行为启用。仿真研究表明，在45纳米技术的基础CMOS设计上，能量提高了20倍。
Deep spiking neural networks are becoming increasingly powerful tools for cognitive computing platforms. However, most of the existing studies on such computing models are developed with limited insights on the underlying hardware implementation, resulting in area and power expensive designs. Although several neuromimetic devices emulating neural operations have been proposed recently, their functionality has been limited to very simple neural models that may prove to be inefficient at complex recognition tasks. In this paper, we venture into the relatively unexplored area of utilizing the inherent device stochasticity of such neuromimetic devices to model complex neural functionalities in a probabilistic framework in the time domain. We consider the implementation of a deep spiking neural network capable of performing high-accuracy and low-latency classification tasks, where the neural computing unit is enabled by the stochastic switching behavior of a magnetic tunnel junction. The simulation studies indicate an energy improvement of 20x over a baseline CMOS design in 45-nm technology.