Collaborative Research: PPoSS: Planning: Hardware-accelerated Trustworthy Deep Neural Network

合作研究:PPoSS:规划:硬件加速的可信深度神经网络

基本信息

  • 批准号:
    2028858
  • 负责人:
  • 金额:
    $ 6万
  • 依托单位:
  • 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 2022-09-30
  • 项目状态:
    已结题

项目摘要

Deep-learning approaches have recently achieved much higher accuracy than traditional machine-learning approaches in various applications (e.g., computer vision, virtual/augmented reality, and natural language processing). Existing research has shown that large-scale data from various sources with high-resolution sensing or large-volume data-collection capabilities can significantly improve the performance of deep-learning approaches. However, state-of-the-art hardware and software cannot provide sufficient computing capabilities and resources to ensure accurate deep-learning performance in a timely manner when using extremely large-scale data. This project develops a scalable and robust heterogeneous system that includes a new low-cost, secure, deep-learning hardware-accelerator architecture and a suite of large-data-compatible deep-learning algorithms. It allows deep learning to fully benefit from extremely large-scale data and facilitates efficient, low-latency applications in connected vehicles, real-time mobile applications, and timely precision health. The new technologies resulting from this project can enable more research opportunities to design new hardware accelerators for deep learning and obtain further optimization in computational complexity and reduction in power consumption. Moreover, by integrating the research results with the undergraduate and graduate curricula and outreach activities, this project has great impacts on education and training of researchers and engineers for computer architecture, security, theory and algorithms, and systems.This project designs trustworthy hardware accelerators optimized for large-scale deep-learning computations and models the complicated structure of large-scale datasets. More specifically, this project develops a novel hardware accelerator for deep learning that can achieve low power consumption. In addition, this project designs innovative in-memory encryption schemes to secure the neural models in deep-learning accelerators. Furthermore, data-modeling and statistical-learning algorithms are developed in this project to further reduce the computing cost of deep learning when processing extremely large-scale datasets. Finally, this project builds and evaluates a prototype of the proposed heterogeneous deep-learning system in terms of efficiency, scalability, and security in multiple application domains including mobile applications, connected vehicles and precision health.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.
深度学习方法最近在各种应用中实现了比传统机器学习方法高得多的准确性(例如,计算机视觉、虚拟/增强现实和自然语言处理)。现有的研究表明,来自各种来源的具有高分辨率传感或大容量数据收集能力的大规模数据可以显着提高深度学习方法的性能。然而,最先进的硬件和软件无法提供足够的计算能力和资源,以确保在使用超大规模数据时及时实现准确的深度学习性能。该项目开发了一个可扩展且强大的异构系统,包括一个新的低成本,安全的深度学习硬件加速器架构和一套大数据兼容的深度学习算法。它允许深度学习充分受益于超大规模数据,并促进互联车辆中的高效、低延迟应用、实时移动的应用和及时的精准健康。该项目产生的新技术可以为设计用于深度学习的新硬件加速器提供更多的研究机会,并进一步优化计算复杂度和降低功耗。此外,通过将研究成果与本科生和研究生课程以及推广活动相结合,该项目对计算机体系结构、安全、理论和算法以及系统的研究人员和工程师的教育和培训产生了重大影响。该项目设计了值得信赖的硬件加速器,为大规模深度学习计算进行了优化,并对大规模数据集的复杂结构进行了建模。更具体地说,该项目开发了一种用于深度学习的新型硬件加速器,可以实现低功耗。此外,该项目还设计了创新的内存加密方案,以保护深度学习加速器中的神经模型。此外,该项目还开发了数据建模和自动学习算法,以进一步降低深度学习在处理超大规模数据集时的计算成本。最后,该项目构建并评估了拟议的异构深度学习系统原型,在多个应用领域(包括移动的应用、联网车辆和精确健康)中的效率、可扩展性和安全性。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(6)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
WatchID: Wearable Device Authentication via Reprogrammable Vibration
WatchID:通过可重新编程的振动进行可穿戴设备身份验证
Defending against Thru-barrier Stealthy Voice Attacks via Cross-Domain Sensing on Phoneme Sounds
通过音素声音的跨域感知防御穿墙隐形语音攻击
Robust Continuous Authentication Using Cardiac Biometrics From Wrist-Worn Wearables
  • DOI:
    10.1109/jiot.2021.3128290
  • 发表时间:
    2022-06
  • 期刊:
  • 影响因子:
    10.6
  • 作者:
    Tianming Zhao;Yan Wang;Jian Liu;Jerry Q. Cheng;Yingying Chen;Jiadi Yu
  • 通讯作者:
    Tianming Zhao;Yan Wang;Jian Liu;Jerry Q. Cheng;Yingying Chen;Jiadi Yu
A Survey of Deep Learning on Mobile Devices: Applications, Optimizations, Challenges, and Research Opportunities
移动设备深度学习调查:应用、优化、挑战和研究机会
  • DOI:
    10.1109/jproc.2022.3153408
  • 发表时间:
    2022
  • 期刊:
  • 影响因子:
    20.6
  • 作者:
    Zhao, Tianming;Xie, Yucheng;Wang, Yan;Cheng, Jerry;Guo, Xiaonan;Hu, Bin;Chen, Yingying
  • 通讯作者:
    Chen, Yingying
mmFit: Low-Effort Personalized Fitness Monitoring Using Millimeter Wave
{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Yan Wang其他文献

Synthesis, structure, and reactivity of .eta.2-1,3-diene and enyne complexes of the chiral rhenium Lewis acid [(.eta.5-C5H5)Re(NO)(PPh3)]+: ozonolysis within a metal coordination sphere
手性铼路易斯酸[(eta.5-C5H5)Re(NO)(PPh3)]的eta2-1,3-二烯和烯炔配合物的合成、结构和反应性:金属配位球内的臭氧分解
  • DOI:
  • 发表时间:
    1993
  • 期刊:
  • 影响因子:
    0
  • 作者:
    T. Peng;Yan Wang;A. Arif;J. Gladysz
  • 通讯作者:
    J. Gladysz
Prevalence and characteristics of cough headache in a Chinese respiratory clinic
我国某呼吸科门诊咳嗽头痛的患病率及特点[J].
  • DOI:
    10.1177/0333102420970187
  • 发表时间:
    2020
  • 期刊:
  • 影响因子:
    4.9
  • 作者:
    Yimo Zhang;Xin Zhao;Yan Wang;Zhao Dong;Shengyuan Yu
  • 通讯作者:
    Shengyuan Yu
An Acetone Sensor Based on Plasma-Assisted Cataluminescence and Mechanism Studies by Online Ionizations.
基于等离子体辅助催化发光的丙酮传感器和在线电离机理研究。
  • DOI:
    10.1021/acs.analchem.9b04023
  • 发表时间:
    2019
  • 期刊:
  • 影响因子:
    7.4
  • 作者:
    Ni Zeng;Zi Long;Yan Wang;Jianghui Sun;Jin Ouyang;Na Na
  • 通讯作者:
    Na Na
Cooperation Diversity for Secrecy Enhancement in Cognitive Relay Wiretap Network Over Correlated Fading Channels
相关衰落信道上认知中继窃听网络保密性增强的合作多样性
  • DOI:
    10.1109/access.2018.2837225
  • 发表时间:
    2018
  • 期刊:
  • 影响因子:
    3.9
  • 作者:
    Mu Li;Hao Yin;Yuzhen Huang;Yan Wang;Rui Yu
  • 通讯作者:
    Rui Yu
Applying the chemical bonding theory of single crystal growth to a Gd3Ga5O12 Czochralski growth system: both thermodynamic and kinetic controls of themesoscale process during single crystal growth
将单晶生长的化学键合理论应用于 Gd3Ga5O12 直拉生长系统:单晶生长过程中尺度过程的热力学和动力学控制
  • DOI:
    10.1039/c5ce00291e
  • 发表时间:
    2015
  • 期刊:
  • 影响因子:
    3.1
  • 作者:
    Yan Wang;Congting Sun;Chaoyang Tu;Dongfeng Xue
  • 通讯作者:
    Dongfeng Xue

Yan Wang的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Yan Wang', 18)}}的其他基金

Spatial Explanation and Planning for Resilience of Community-Based Small Businesses to Environmental Shocks
基于社区的小型企业对环境冲击的抵御能力的空间解释和规划
  • 批准号:
    2316450
  • 财政年份:
    2023
  • 资助金额:
    $ 6万
  • 项目类别:
    Standard Grant
Collaborative Research: III: Small: Efficient and Robust Multi-model Data Analytics for Edge Computing
协作研究:III:小型:边缘计算的高效、稳健的多模型数据分析
  • 批准号:
    2311597
  • 财政年份:
    2023
  • 资助金额:
    $ 6万
  • 项目类别:
    Standard Grant
Collaborative Research: Cross-plane Heat Conduction in 2D Materials under Large Compressive Strain
合作研究:大压缩应变下二维材料的横向热传导
  • 批准号:
    2211696
  • 财政年份:
    2022
  • 资助金额:
    $ 6万
  • 项目类别:
    Standard Grant
CAREER: Efficient Mobile Edge Oriented Deep Learning Framework
职业:高效的面向移动边缘的深度学习框架
  • 批准号:
    2145389
  • 财政年份:
    2022
  • 资助金额:
    $ 6万
  • 项目类别:
    Continuing Grant
Collaborative Research: CCRI: New: Nation-wide Community-based Mobile Edge Sensing and Computing Testbeds
合作研究:CCRI:新:全国范围内基于社区的移动边缘传感和计算测试平台
  • 批准号:
    2120276
  • 财政年份:
    2021
  • 资助金额:
    $ 6万
  • 项目类别:
    Standard Grant
CAREER: Fundamental Investigation of the Wave Nature of Lattice Thermal Transport
职业:晶格热传输波性质的基础研究
  • 批准号:
    2047109
  • 财政年份:
    2021
  • 资助金额:
    $ 6万
  • 项目类别:
    Continuing Grant
SCC-PG: SmartCurb: Building Smart Urban Curb Environments
SCC-PG:SmartCurb:构建智能城市路缘环境
  • 批准号:
    2124858
  • 财政年份:
    2021
  • 资助金额:
    $ 6万
  • 项目类别:
    Standard Grant
RII Track-4: Low-temperature Laser Sintering and Melting of Semiconductors Through Selective Excitation of Soft Phonons
RII Track-4:通过软声子的选择性激发实现半导体的低温激光烧结和熔化
  • 批准号:
    2033424
  • 财政年份:
    2021
  • 资助金额:
    $ 6万
  • 项目类别:
    Standard Grant
RAPID: Dynamic Interactions between Human and Information in Complex Online Environments Responding to SARS-COV-2
RAPID:复杂在线环境中人与信息之间的动态交互,应对 SARS-COV-2
  • 批准号:
    2028012
  • 财政年份:
    2020
  • 资助金额:
    $ 6万
  • 项目类别:
    Standard Grant
CDS&E: Nanoconfined Heating via Ultrahigh-repetition-rate Lasers for Enhanced Surface Processing
CDS
  • 批准号:
    1953300
  • 财政年份:
    2020
  • 资助金额:
    $ 6万
  • 项目类别:
    Standard Grant

相似国自然基金

Research on Quantum Field Theory without a Lagrangian Description
  • 批准号:
    24ZR1403900
  • 批准年份:
    2024
  • 资助金额:
    0.0 万元
  • 项目类别:
    省市级项目
Cell Research
  • 批准号:
    31224802
  • 批准年份:
    2012
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Cell Research
  • 批准号:
    31024804
  • 批准年份:
    2010
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Cell Research (细胞研究)
  • 批准号:
    30824808
  • 批准年份:
    2008
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Research on the Rapid Growth Mechanism of KDP Crystal
  • 批准号:
    10774081
  • 批准年份:
    2007
  • 资助金额:
    45.0 万元
  • 项目类别:
    面上项目

相似海外基金

Collaborative Research: PPoSS: Large: A Full-stack Approach to Declarative Analytics at Scale
协作研究:PPoSS:大型:大规模声明性分析的全栈方法
  • 批准号:
    2316161
  • 财政年份:
    2023
  • 资助金额:
    $ 6万
  • 项目类别:
    Continuing Grant
Collaborative Research: PPoSS: LARGE: Research into the Use and iNtegration of Data Movement Accelerators (RUN-DMX)
协作研究:PPoSS:大型:数据移动加速器 (RUN-DMX) 的使用和集成研究
  • 批准号:
    2316176
  • 财政年份:
    2023
  • 资助金额:
    $ 6万
  • 项目类别:
    Continuing Grant
Collaborative Research: PPoSS: Large: A Full-stack Approach to Declarative Analytics at Scale
协作研究:PPoSS:大型:大规模声明性分析的全栈方法
  • 批准号:
    2316158
  • 财政年份:
    2023
  • 资助金额:
    $ 6万
  • 项目类别:
    Continuing Grant
Collaborative Research: PPoSS: LARGE: Cross-layer Coordination and Optimization for Scalable and Sparse Tensor Networks (CROSS)
合作研究:PPoSS:LARGE:可扩展和稀疏张量网络的跨层协调和优化(CROSS)
  • 批准号:
    2316201
  • 财政年份:
    2023
  • 资助金额:
    $ 6万
  • 项目类别:
    Standard Grant
Collaborative Research: PPoSS: LARGE: Cross-layer Coordination and Optimization for Scalable and Sparse Tensor Networks (CROSS)
合作研究:PPoSS:LARGE:可扩展和稀疏张量网络的跨层协调和优化(CROSS)
  • 批准号:
    2316203
  • 财政年份:
    2023
  • 资助金额:
    $ 6万
  • 项目类别:
    Continuing Grant
Collaborative Research: PPoSS: LARGE: Research into the Use and iNtegration of Data Movement Accelerators (RUN-DMX)
协作研究:PPoSS:大型:数据移动加速器 (RUN-DMX) 的使用和集成研究
  • 批准号:
    2316177
  • 财政年份:
    2023
  • 资助金额:
    $ 6万
  • 项目类别:
    Continuing Grant
Collaborative Research: PPoSS: LARGE: Cross-layer Coordination and Optimization for Scalable and Sparse Tensor Networks (CROSS)
合作研究:PPoSS:LARGE:可扩展和稀疏张量网络的跨层协调和优化(CROSS)
  • 批准号:
    2316202
  • 财政年份:
    2023
  • 资助金额:
    $ 6万
  • 项目类别:
    Standard Grant
Collaborative Research: PPoSS: LARGE: General-Purpose Scalable Technologies for Fundamental Graph Problems
合作研究:PPoSS:大型:解决基本图问题的通用可扩展技术
  • 批准号:
    2316235
  • 财政年份:
    2023
  • 资助金额:
    $ 6万
  • 项目类别:
    Continuing Grant
Collaborative Research: PPoSS: LARGE: Principles and Infrastructure of Extreme Scale Edge Learning for Computational Screening and Surveillance for Health Care
合作研究:PPoSS:大型:用于医疗保健计算筛查和监视的超大规模边缘学习的原理和基础设施
  • 批准号:
    2406572
  • 财政年份:
    2023
  • 资助金额:
    $ 6万
  • 项目类别:
    Continuing Grant
Collaborative Research: PPoSS: Large: A Full-stack Approach to Declarative Analytics at Scale
协作研究:PPoSS:大型:大规模声明性分析的全栈方法
  • 批准号:
    2316159
  • 财政年份:
    2023
  • 资助金额:
    $ 6万
  • 项目类别:
    Continuing Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了