arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2011.11840cs.LGcs.AIcs.ARcs.CVcs.PF
收藏

ADI公司深度学习模型的基准推理性能

Benchmarking Inference Performance of Deep Learning Models on Analog Devices

Prairie View A&M University(普雷里维尤农工大学);Texas A&M University System(德州农工大学系统)

Omobayode Fagbohungbe, Lijun Qian

摘要:

模拟硬件实现的深度学习模型对于诸如边缘计算设备之类的计算和能量受限的系统是有希望的。然而,设备的模拟性质和相关联的许多噪声源将导致部署在此类设备上的经训练的深度学习模型中的权重值的改变。在这项研究中,系统地评估了模拟设备上部署的用于图像分类的受训练的流行深度学习模型的推理性能,其中在推理期间将加性高斯白噪声添加到受训练模型的权重中。据观察,更深的模型和设计中具有更多冗余的模型(如VGG)通常对噪声更具鲁棒性。然而,性能也受到模型的设计理念、模型的详细结构、确切的机器学习任务以及数据集的影响。

英文摘要:

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.

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。

↑