SHF: Small: A Design Automation Methodology for Flexible Real-Time Computing based on Split and Early Exit Neural Models

SHF：小型：基于分裂和早期退出神经模型的灵活实时计算的设计自动化方法

基本信息

批准号：
2140154
负责人：
Mohammad Al Faruque
金额：
$ 50万
依托单位：
University of California-Irvine
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2022
资助国家：
美国
起止时间：
2022-02-01 至 2025-01-31
项目状态：
未结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2140154&HistoricalAwards=false
关键词：
SHF Small Design Automation Methodology

项目摘要

The overarching goal of this project is to develop highly adaptable deep-learning (DL) frameworks for real-time applications, such as autonomous vehicles and mobile health. To this aim, the proposed design-automation methodology will bridge runtime system optimization with advanced DL model architectures, through leveraging the techniques of split computing (SC) and early-exit computation (EEC). In traditional methodologies, the design process of a DL model is performed in isolation, where its structure is optimized with respect to a dataset and fixed system conditions. Instead, the new frameworks will jointly use SC and EEC to build DL models specifically designed to adapt real-time data analysis to time-varying characteristics of the system (e.g., available energy, computing power, channel capacity, computing task, etc.) and the information stream. To accomplish this objective, the team will use tools such as deep reinforcement learning and neural architecture search. The project will include a well-laid out educational and outreach plan, in which the involvement of undergraduate and graduate students is particularly promising. The project also proposes a suite of university initiatives which they will leverage to enhance diversity during the execution of this project.The research endeavor will produce frameworks that are expected to considerably boost the performance of critical applications such as autonomous vehicles and AI-empowered monitoring for mobile health while reducing their energy consumption and wireless channel usage. Software and simulation artifacts will be released as open-source platforms to enhance research in this important area.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.

该项目的总体目标是为自动驾驶汽车和移动健康等实时应用开发高度适应性的深度学习 (DL) 框架。为此，所提出的设计自动化方法将通过利用分割计算（SC）和提前退出计算（EEC）技术，将运行时系统优化与先进的深度学习模型架构联系起来。在传统方法中，深度学习模型的设计过程是独立执行的，其结构根据数据集和固定系统条件进行优化。相反，新框架将联合使用 SC 和 EEC 来构建专门设计的深度学习模型，使实时数据分析适应系统的时变特征（例如可用能量、计算能力、通道容量、计算任务等）。和信息流。为了实现这一目标，该团队将使用深度强化学习和神经架构搜索等工具。该项目将包括一个精心设计的教育和推广计划，其中本科生和研究生的参与尤其有希望。该项目还提出了一系列大学举措，大学将利用这些举措在项目执行过程中增强多样性。这项研究工作将产生框架，预计将显着提高自动驾驶汽车和人工智能监控等关键应用的性能。移动健康，同时减少能源消耗和无线信道使用。软件和模拟工件将作为开源平台发布，以加强这一重要领域的研究。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

期刊论文数量（19）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

MaGNAS: A Mapping-Aware Graph Neural Architecture Search Framework for Heterogeneous MPSoC Deployment

MaGNAS：用于异构 MPSoC 部署的映射感知图神经架构搜索框架

DOI：
10.1145/3609386
发表时间：
2023-07-16
期刊：
ACM Transactions on Embedded Computing Systems
影响因子：
2
作者：
Mohanad Odema;Halima Bouzidi;Hamza Ouarnoughi;S. Niar;M. A. Al Faruque
通讯作者：
M. A. Al Faruque

DOMINO: Domain-Invariant Hyperdimensional Classification for Multi-Sensor Time Series Data

DOMINO：多传感器时间序列数据的域不变超维分类

DOI：
10.1109/iccad57390.2023.10323848
发表时间：
2023-08-07
期刊：
2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD)
影响因子：
0
作者：
Junyao Wang;Luke Chen;M. A. Faruque
通讯作者：
M. A. Faruque

PrivyNAS: Privacy-Aware Neural Architecture Search for Split Computing in Edge-Cloud Systems

PrvyNAS：边缘云系统中用于分割计算的隐私感知神经架构搜索

DOI：
10.1109/jiot.2023.3311761
发表时间：
2023-01
期刊：
IEEE Internet of Things Journal
影响因子：
10.6
作者：
Odema, Mohanad;Faruque, Mohammad Abdullah
通讯作者：
Faruque, Mohammad Abdullah

Template Matching Based Early Exit CNN for Energy-efficient Myocardial Infarction Detection on Low-power Wearable Devices

基于模板匹配的早期退出 CNN，用于低功耗可穿戴设备上的节能心肌梗塞检测

DOI：
10.1145/3534580
发表时间：
2022-07
期刊：
Wearable and Ubiquitous Technologies
影响因子：
0
作者：
Rashid, Nafiul;Demirel, Berken Utku;Odema, Mohanad;Al Faruque, Mohammad Abdullah
通讯作者：
Al Faruque, Mohammad Abdullah

Stress Detection Using Context-Aware Sensor Fusion From Wearable Devices

使用可穿戴设备的上下文感知传感器融合进行压力检测