Quantized neural networks (QNNs) are being actively researched as a solution for the computational complexity and memory intensity of deep neural networks. This has sparked efforts to develop algorithms that support both inference and training with quantized weight and activation values, without sacrificing accuracy. A recent example is the GXNOR framework for stochastic training of ternary (TNN) and binary (BNN) neural networks. In this paper, we show how magnetic tunnel junction (MTJ) devices can be used to support QNN training. We introduce a novel hardware synapse circuit that uses the MTJ stochastic behavior to support the quantize update. The proposed circuit enables processing near memory (PNM) of QNN training, which subsequently reduces data movement. We simulated MTJ-based stochastic training of a TNN over the MNIST, SVHN, and CIFAR10 datasets and achieved an accuracy of 98.61%, 93.99% and 82.71%, respectively (less than 1% degradation compared to the GXNOR algorithm). We evaluated the synapse array performance potential and showed that the proposed synapse circuit can train ternary networks in situ, with 18.3TOPs/W for feedforward and 3TOPs/W for weight update.
翻译:量化神经网络(QNN)是作为计算复杂度和深神经网络记忆强度的一种解决方案而积极研究的。这引发了开发算法的努力,这种算法既支持以量化的重量和激活值进行推断和培训,又不牺牲准确性。最近的一个例子是GXNOR对永恒神经网络和二进制神经网络进行透视培训的框架。在本文中,我们展示了如何利用磁隧道连接装置来支持QNNN培训。我们引入了新型硬件突触电路,利用MTJ透视行为支持量化更新。拟议的电路使QNNN培训能够在近距离内处理记忆(PNM),从而减少数据移动。我们模拟了以MTJ为基础的对NN在MIST、SVHN和CIFAR10网络上进行抽查培训,并实现了98.61%、93.99%和82.71%的精确度。我们用GXNGPS-P Retrocal 数据网络展示了18度的变质/变压。我们用GXNOR 3的变压阵列/变压网络展示了该变压。