Accelerating Deep Neural Networks with Analog Memory Devices
Accelerating Deep Neural Networks with Analog Memory Devices
复制标题
使用模拟存储设备加速深度神经网络
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
An Chen
中科院分区：
文献类型：
--
作者：
G. Burr;S. Ambrogio;P. Narayanan;H. Tsai;C. Mackin;An Chen
深度神经网络(DNN)是使用非常大的数据集训练的非常大的人工神经网络，通常使用称为反向传播的有监督学习技术。目前，这些计算使用的是CPU和GPU。在接下来的几年里，我们可以期待基于传统数字设计技术的专用硬件加速器来优化用于这些DNN计算的GPU框架。在这里，有两个不同但相关的任务：训练和前向推理，有机会提高速度和降低功率。在训练期间，DNN的权重被调整，以通过重复暴露于标记的数据来提高网络性能--大数据集的例子。这通常涉及在云中协同工作的分布式芯片网络。在正向推理过程中，已经训练好的网络被用来分析新的数据--例如，有时在延迟受限的云环境中，有时在功率受限的环境中(传感器、移动电话、网络边缘设备等)。即使在这些特殊用途的数字加速器预期的计算性能和效率得到改善之后，基于模拟记忆的神经形态计算仍将有机会获得更高的性能和更好的能效(图1)。
Deep Neural Networks (DNNs) are very large artificial neural networks trained using very large datasets, typically using the supervised learning technique known as backpropagation. Currently, CPUs and GPUs are used for these computations.Over the next few years, we can expect special-purpose hardware accelerators based on conventional digital-design techniques to optimize the GPU framework for these DNN computations. Here there are opportunities to increase speed and reduce power for two distinct but related tasks: training and forward-inference. During training, the weights of a DNN are adjusted to improve network performance through repeated exposure to the labelled data-examples of a large dataset. Often this involves a distributed network of chips working together in the cloud. During forward-inference, already trained networks are used to analyze new data-examples, sometimes in a latency-constrained cloud environment and sometimes in a power-constrained environment (sensors, mobile phones, “edge-of-network” devices, etc.)Even after the improved computational performance and efficiency that is expected from these special-purpose digital accelerators, there would still be an opportunity for even higher performance and even better energy-efficiency from neuromorphic computation based on analog memories (Fig. 1).