论文标题
基准在模拟设备上深度学习模型的推理性能
Benchmarking Inference Performance of Deep Learning Models on Analog Devices
论文作者
论文摘要
实施的模拟硬件深度学习模型对于计算和能量约束系统（例如边缘计算设备）都是有希望的。但是，设备的模拟性质和相关的许多噪声源将导致在部署在此类设备上的训练有素的深度学习模型中的权重价值变化。在这项研究中，已经对在模拟设备上部署的受过训练的流行深度学习模型的推理性能进行了系统评估，在推理过程中，在训练有素的模型的重量中添加了添加的白色高斯噪声。据观察，在设计（例如VGG）中具有更高冗余性的更深层次模型和模型通常对噪声更强大。但是，性能还受模型的设计理念，模型的详细结构，确切的机器学习任务以及数据集的影响。
Analog hardware implemented deep learning models are promising for computation and energy constrained systems such as edge computing devices. However, the analog nature of the device and the associated many noise sources will cause changes to the value of the weights in the trained deep learning models deployed on such devices. In this study, systematic evaluation of the inference performance of trained popular deep learning models for image classification deployed on analog devices has been carried out, where additive white Gaussian noise has been added to the weights of the trained models during inference. It is observed that deeper models and models with more redundancy in design such as VGG are more robust to the noise in general. However, the performance is also affected by the design philosophy of the model, the detailed structure of the model, the exact machine learning task, as well as the datasets.
