论文标题
使用随机计算的神经网络加速的设计挑战
Design Challenges of Neural Network Acceleration Using Stochastic Computing
论文作者
论文摘要
最先进的神经网络（NNS）的巨大和不断增强的复杂性阻碍了对资源有限的设备（例如物联网）（IoT）的深入学习的部署。随机计算利用了NNS的近似特征的固有的不合适性，以减少其能量和面积足迹，这是适合IoT的小型嵌入式设备的两个关键要求。该报告评估并比较了最近提出的两个基于随机的NN设计，该设计由Sim和Lee，2017年，Canals等人，2016年。通过分析和模拟，我们比较了这些设计的三个截然不同的实现，从而比较了这些设计的三个截然不同的实现。我们还讨论采用随机计算对建筑NNS所面临的总体挑战。我们发现，在执行应用于MNIST数字识别数据集的LENET-5 NN模型时，BISC胜过其他体系结构。我们的分析和仿真实验表明，与两个ESL体系结构相比，该体系结构的速度更快约50倍，面积少5.7倍和2.9倍，消耗7.8倍和1.8倍的功率。
The enormous and ever-increasing complexity of state-of-the-art neural networks (NNs) has impeded the deployment of deep learning on resource-limited devices such as the Internet of Things (IoTs). Stochastic computing exploits the inherent amenability to approximation characteristic of NNs to reduce their energy and area footprint, two critical requirements of small embedded devices suitable for the IoTs. This report evaluates and compares two recently proposed stochastic-based NN designs, referred to as BISC (Binary Interfaced Stochastic Computing) by Sim and Lee, 2017, and ESL (Extended Stochastic Logic) by Canals et al., 2016. Using analysis and simulation, we compare three distinct implementations of these designs in terms of performance, power consumption, area, and accuracy. We also discuss the overall challenges faced in adopting stochastic computing for building NNs. We find that BISC outperforms the other architectures when executing the LeNet-5 NN model applied to the MNIST digit recognition dataset. Our analysis and simulation experiments indicate that this architecture is around 50X faster, occupies 5.7X and 2.9X less area, and consumes 7.8X and 1.8X less power than the two ESL architectures.
