CSR: Small:Collaborative Research: Decentralized Real-Time Machine Learning Systems on Near-User Edge Devices

CSR：小型：协作研究：近用户边缘设备上的分散式实时机器学习系统

• 批准号: 1815047
• 负责人: Hyesoon Kim
• 金额: $ 25万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-10-01 至 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1815047&HistoricalAwards=false
• 关键词: CSR; Small; Collaborative; Research; Decentralized

The ever-increasing number of Internet of Things (IoT) devices generate large quantities of raw data that need to be processed and analyzed in real time. Since conducting computationally expensive tasks, such as computer vision and natural language processing, is often a challenge for IoT devices, most of their computations are currently offloaded to cloud servers. However, this offloading leads to an increased risk for privacy as well as a dependency on network connectivity. To solve this challenge, the project utilizes the distributed computing power of already connected IoT devices to perform high computing power applications in real time.The project is composed of three tasks. First is the development of distributed machine learning (ML) systems for multiple IoT devices. The project will involve studying how to communicate between nodes with reliable connections and how to dynamically change the job of each node at run-time with little overhead. Second is the development of optimal task assignment and scheduling algorithms. Here, a machine learning approach will be used to generate a recognition model architecture optimal for each distributed system configuration. Third is the development of low-resolution deep neural network (DNN) systems to utilize low-power computing nodes. The development of these DNN systems will involve identifying multiple low-resolution filters that are optimal for varying configurations.The proposed technical work will advance the state of the art in implementation of parallel and decentralized DNN systems, thereby benefiting all scientific fields of endeavor that rely on computing. The decentralized DNN system will offer new opportunities in power constrained mobile platforms for applications including surveillance and automotive. The research results will lead to new materials/courses for computer architecture and systems. The proposed infrastructure will also be used to guide undergraduate students' research activities. The software infrastructure will be maintained as an open source project, which can be found at https://github.com/parallel-ml. It will be updated periodically as new outcomes become available. The results will be published in conferences, journals and technical reports.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

数量不断增加的物联网（IoT）设备会生成大量的原始数据，需要实时处理和分析。 由于进行计算昂贵的任务（例如计算机视觉和自然语言处理）通常是物联网设备的挑战，因此他们的大多数计算目前都被卸载到云服务器上。但是，这种卸载会导致隐私风险增加以及对网络连接性的依赖。为了解决这一挑战，该项目利用已经连接的物联网设备的分布式计算能力实时执行高计算功率应用程序。该项目由三个任务组成。首先是用于多个物联网设备的分布式机器学习（ML）系统的开发。 该项目将涉及研究如何与可靠的连接之间的节点之间进行交流，以及如何在运行时动态更改每个节点的作业，而没有开销。第二是开发最佳任务分配和调度算法。在这里，机器学习方法将用于生成针对每种分布式系统配置的最佳识别模型体系结构。第三是低分辨率深神经网络（DNN）系统的开发来利用低功率计算节点。这些DNN系统的开发将涉及确定多个低分辨率过滤器，这些过滤器最适合各种配置。拟议的技术工作将推动实施并行和分散的DNN系统实施最新技术，从而使所有依赖计算的EndeAvor的科学领域受益。分散的DNN系统将为包括监视和汽车在内的应用程序提供新的机会。研究结果将为计算机架构和系统提供新的材料/课程。拟议的基础设施还将用于指导本科生的研究活动。该软件基础架构将作为一个开源项目维护，可以在https://github.com/parallelal-ml上找到。 随着新结果的可用，它将定期更新。结果将在会议，期刊和技术报告中发表。该奖项反映了NSF的法定任务，并被认为是值得通过基金会的知识分子优点和更广泛影响的评论标准来评估值得支持的。

项目成果

SmaQ: Smart Quantization for DNN Training by Exploiting Value Clustering

• DOI: 10.1109/lca.2021.3108505
• 发表时间: 2021-07
• 期刊: IEEE Computer Architecture Letters
• 影响因子: 2.3
• 作者: Nima Shoghi;Andrei Bersatti;Moinuddin K. Qureshi;Hyesoon Kim

Video analytics from edge to server: work-in-progress

从边缘到服务器的视频分析：正在进行中

• 发表时间: 2019
• 期刊: CODES/ISSS '19: Proceedings of the International Conference on Hardware/Software Codesign and System Synthesis Companion
• 作者: Jiashen Cao, Ramyad Hadidi

Characterizing the Deployment of Deep Neural Networks on Commercial Edge Devices

• DOI: 10.1109/iiswc47752.2019.9041955
• 发表时间: 2019-01-01
• 期刊: PROCEEDINGS OF THE 2019 IEEE INTERNATIONAL SYMPOSIUM ON WORKLOAD CHARACTERIZATION (IISWC 2019)
• 作者: Hadidi, Ramyad;Cao, Jiashen;Kim, Hyesoon
• 通讯作者: Kim, Hyesoon

Distributed Perception by Collaborative Robots

• DOI: 10.1109/lra.2018.2856261
• 发表时间: 2018-07
• 期刊: IEEE Robotics and Automation Letters
• 影响因子: 5.2
• 作者: Ramyad Hadidi;Jiashen Cao;M. Woodward;M. Ryoo;Hyesoon Kim

FiGO: Fine-Grained Query Optimization in Video Analytics

• DOI: 10.1145/3514221.3517857
• 发表时间: 2022-06
• 期刊: Proceedings of the 2022 International Conference on Management of Data
• 作者: Jiashen Cao;Karan Sarkar;Ramyad Hadidi;Joy Arulraj;Hyesoon Kim