使用随机计算加速神经网络的设计挑战
Design Challenges of Neural Network Acceleration Using Stochastic Computing
摘要：
最先进的神经网络（NN）的巨大且不断增加的复杂性阻碍了深度学习在物联网（IoT）等资源有限的设备上的部署。随机计算利用了NN的固有的对近似特性的适应性，以减少其能量和面积占用，这是适合物联网的小型嵌入式设备的两个关键要求。本报告评估和比较了两种最近提出的基于随机的NN设计，Sim和Lee，2017年称为BISC（二进制接口随机计算），以及Canals等人的ESL（扩展随机逻辑）。2016.使用分析和仿真，我们比较这些设计的三个不同的实现在性能，功耗，面积和精度。我们还讨论了采用随机计算构建NN所面临的总体挑战。我们发现，BISC优于其他架构时，执行的LeNet-5 NN模型应用到MNIST数字识别数据集。我们的分析和模拟实验表明，这种架构是大约50倍的速度，占用5.7倍和2.9倍的面积少，并消耗7.8倍和1.8倍的功耗比两个ESL架构。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
