Mixed-mode Magnetic Tunnel Junction-based Deep Belief Network
Mixed-mode Magnetic Tunnel Junction-based Deep Belief Network
复制标题
基于混合模式磁隧道结的深度置信网络
DOI：
10.1109/nano46743.2019.8993914
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
A. Trivedi
中科院分区：
文献类型：
--
作者：
Shamma Nasrin;J. Drobitch;Supriyo Bandyopadhyay;A. Trivedi
提出了一种基于混合模式磁隧道结（m-MTJ）的深度信念网络（DBN）。DBN是无监督学习模型，适用于识别和聚类。m-MTJ是一种三端磁性器件，其概率自由层切换由电压控制的磁各向异性和自旋转移矩的同时作用控制。虽然DBN即使在高度不精确的单比特权重下也能实现高预测精度，但关键的复杂性在于它们的随机激活函数。使用m-MTJ，我们提出了一种新的低面积/功率DBN神经元与随机激活功能。我们讨论了一个内存计算架构，允许向前和向后流动的学习动态和在线学习。我们的设计在MNIST中实现了~88.80%的数字识别准确率，即使在纳米级m-MTJ的最坏情况下也是如此。
We present a mixed-mode magneto tunneling junction (m-MTJ)-based Deep Belief Network (DBN). DBNs are unsupervised learning models, suitable for recognition and clustering. m-MTJ is a three-terminal magnetic device with probabilistic free layer switching controlled by the simultaneous actions of voltage-controlled magnetic anisotropy and spin-transfer torque. While DBNs achieve high prediction accuracy even with highly imprecise single-bit weights, the key complexity lies in their activation functions which are stochastic. Using an m-MTJ, we present a novel low area/power DBN neuron with stochastic activation function. We discuss an in-memory computing architecture that allows forward and backward flow of learning dynamics and online learning. Our design achieves ~88.80% accuracy for digit recognition in MNIST even under the worst case variability in nanoscaled m-MTJs.