arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.09274cs.LG
收藏

移动设备上的深度学习-综述

Deep Learning on Mobile Devices - A Review

FAST Labs, BAE Systems, Inc.(BAE系统公司FAST实验室)

Yunbin Deng

摘要:

最近在深度学习和人工智能技术方面的突破使众多移动应用成为可能。虽然传统的计算范例依赖于移动传感和云计算,但在移动设备上实现的深度学习提供了若干优点。这些优点包括低通信带宽、小云计算资源成本、快速响应时间和改进的数据隐私。深度学习在移动和嵌入式设备上的研究和开发最近引起了广泛关注。本文及时回顾了这个快节奏的领域,让研究人员,工程师,从业者和研究生快速掌握移动设备上深度学习的最新进展。在本文中,我们讨论了移动深度学习的硬件架构,包括现场可编程门阵列,专用集成电路,以及最近的移动图形处理单元。我们提出的大小,重量,面积和功率的考虑因素及其关系的算法优化,如量化,修剪,压缩和近似,简化计算,同时保持性能的准确性。我们涵盖了现有的系统,并对TensorFlow、MXNet、移动AI计算引擎和Paddle-mobile深度学习平台进行了行业回顾。我们讨论了移动深度学习实践者的资源,包括工具、库、模型和性能基准测试。我们将各种移动传感模式应用于各行各业,从机器人、医疗保健和多媒体、生物识别到自动驾驶和国防。我们解决了需要克服的关键深度学习挑战,包括低质量数据和小训练/适应数据集。此外,该评论提供了大量引用和链接到实现各种技术的现有代码库。

英文摘要:

Recent breakthroughs in deep learning and artificial intelligence technologies have enabled numerous mobile applications. While traditional computation paradigms rely on mobile sensing and cloud computing, deep learning implemented on mobile devices provides several advantages. These advantages include low communication bandwidth, small cloud computing resource cost, quick response time, and improved data privacy. Research and development of deep learning on mobile and embedded devices has recently attracted much attention. This paper provides a timely review of this fast-paced field to give the researcher, engineer, practitioner, and graduate student a quick grasp on the recent advancements of deep learning on mobile devices. In this paper, we discuss hardware architectures for mobile deep learning, including Field Programmable Gate Arrays, Application Specific Integrated Circuit, and recent mobile Graphic Processing Units. We present Size, Weight, Area and Power considerations and their relation to algorithm optimizations, such as quantization, pruning, compression, and approximations that simplify computation while retaining performance accuracy. We cover existing systems and give a state-of-the-industry review of TensorFlow, MXNet, Mobile AI Compute Engine, and Paddle-mobile deep learning platform. We discuss resources for mobile deep learning practitioners, including tools, libraries, models, and performance benchmarks. We present applications of various mobile sensing modalities to industries, ranging from robotics, healthcare and multi-media, biometrics to autonomous drive and defense. We address the key deep learning challenges to overcome, including low quality data, and small training/adaptation data sets. In addition, the review provides numerous citations and links to existing code bases implementing various technologies.

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。

↑