Uncertainty Modeling of Emerging Device based Computing-in-Memory Neural Accelerators with Application to Neural Architecture Search
Uncertainty Modeling of Emerging Device based Computing-in-Memory Neural Accelerators with Application to Neural Architecture Search
复制标题
DOI：
10.1145/3394885.3431635
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Zheyu Yan;Da-Cheng Juan;X. Hu;Yiyu Shi
中科院分区：
文献类型：
--
作者：
Zheyu Yan;Da-Cheng Juan;X. Hu;Yiyu Shi
基于设备的内存计算(CIM)已被证明是高能效深度神经网络(DNN)计算的一种很有前途的候选方法。然而，大多数新兴设备都存在不确定性问题，导致实际存储的数据与设计的权重值之间存在差异。这导致从训练有素的模型到实际部署的平台的精确度下降。在这项工作中，我们对DNN模型中这种不确定性引起的变化的影响进行了深入的分析。为了减少设备不确定性的影响，我们提出了一种不确定性感知的神经结构搜索方案UAE，用于识别对设备不确定性既准确又健壮的DNN模型。
Emerging device based Computing-in-memory (CiM) has been proved to be a promising candidate for high energy efficiency deep neural network (DNN) computations. However, most emerging devices suffer uncertainty issues, resulting in a difference between actual data stored and the weight value it is design to be. This leads to an accuracy drop from trained models to actually deployed platforms. In this work, we offer a thorough analysis on the effect of such uncertainties induced changes in DNN models. To reduce the impact of device uncertainties, we propose UAE, a uncertainty-aware Neural Architecture Search scheme to identify a DNN model that is both accurate and robust against device uncertainties.