SHF: Small: Synthesis of Complex Deep Neural Networks on Distributed Resource-Constrained Devices

SHF：小型：分布式资源受限设备上复杂深度神经网络的综合

• 批准号: 2006394
• 负责人: Azadeh Davoodi
• 金额: $ 49.99万
• 依托单位: University of Wisconsin-Madison
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2006394&HistoricalAwards=false
• 关键词: SHF; Small; Synthesis; Complex; Deep; SHF; Small; Synthesis; Complex; Deep

Deep neural network (DNN) machine learning algorithms have become significantly complex in order to address challenges in modern Information Technology applications such as smart city, autonomous driving, pervasive health care, among others. This complexity necessitates execution on high-end computing platforms which typically reside in a cloud infrastructure. Such applications rely on simple Internet of Things (IoT) devices, such as sensors, to gather data, which typically transfer their data via network to the cloud infrastructure for DNN processing and then receive back an inference. However, such an approach is not scalable to the billions of IoT devices that are projected in the near future. In addition, it cannot work when the network infrastructure is unavailable, and may not allow customization to learn from individual needs or for specific environments. In this project, new techniques will be investigated to directly deploy complex DNNs onto simple IoT devices which work in parallel, with the primary goal to perform an inference task as fast as possible. Technology developed in this project will enable rapid development of smart IoT devices, which can serve as fundamental building blocks of next generation smart services. The research outcomes will be disseminated through intellectual property filing, publication, lectures, and software distribution. They will also be integrated as new curriculum materials into existing courses. Graduate and undergraduate students will be involved in the research activities, with an effort to recruit from women and underrepresented minorities.Specific research activities include: (1) exploring a new methodology to synthesize a complex DNN as a collection of smaller DNNs which are mapped to distributed IoT devices; (2) developing "class-aware" structure simplification techniques to aggressively prune any of the small DNNs when the goal is to cover a subset of the label space on a single IoT device and generate a "don't know" signal for the rest; (3) enhancing the inference accuracy via performing low-cost customizations which arise from usage and environmental factors, when implemented locally on each IoT device.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.

深度神经网络（DNN）机器学习算法已经变得非常复杂，以应对现代信息技术应用程序（例如智能城市，自动驾驶，普遍医疗保健等）的挑战。这种复杂性需要在通常位于云基础架构中的高端计算平台上执行。此类应用程序依靠简单的物联网（IoT）设备（例如传感器）来收集数据，这些数据通常通过网络将其数据传输到云基础架构进行DNN处理，然后再收回推理。但是，这种方法无法扩展到在不久的将来预测的数十亿个IoT设备。此外，当网络基础架构不可用时，它无法正常工作，并且可能不允许自定义从个人需求或特定环境中学习。在该项目中，将研究新技术，将复杂的DNN直接部署到并行起作用的简单IoT设备上，其主要目标是尽快执行推理任务。该项目开发的技术将使智能物联网设备的快速开发可以作为下一代智能服务的基本构建基础。研究成果将通过知识产权归档，出版，讲座和软件分发来传播。它们还将作为新课程材料集成到现有课程中。 研究生和本科生将参与研究活动，并努力从妇女和代表性不足的少数群体中招募。特定的研究活动包括：（1）探索一种新的方法，以合成复杂的DNN，作为较小的DNN的集合，这些DNN映射到分布式的IoT设备； （2）开发“阶级意识”结构简化技术，以积极修剪任何小型DNN，而目标是覆盖单个物联网设备上的标签空间的子集并为其余的“不知道”信号生成“不知道”信号； （3）通过执行源于用法和环境因素的低成本自定义来提高推理准确性，当在每个物联网设备上实施时。该奖项反映了NSF的法定任务，并被认为值得通过基金会的知识分子优点和更广泛的审查标准通过评估来进行评估。