RTML: Large: Collaborative: Harmonizing Predictive Algorithms and Mixed-Signal/Precision Circuits via Computation-Data Access Exchange and Adaptive Dataflows

RTML:大型:协作:通过计算数据访问交换和自适应数据流协调预测算法和混合信号/精密电路

基本信息

  • 批准号:
    1937592
  • 负责人:
  • 金额:
    $ 58.53万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2019
  • 资助国家:
    美国
  • 起止时间:
    2019-10-01 至 2024-04-30
  • 项目状态:
    已结题

项目摘要

Recent advances in machine learning are fueling a growing demand for intelligent Internet of Things (IoT), i.e., edge network applications. Many of them, such as autonomous vehicles, robots, and healthcare wearables, require real-time and in-situ learning to be perceived as truly intelligent. However, the limited computing and energy resources available at the edge device (e.g., mobile devices, sensors) stand at odds with the massive and growing cost of state-of-the-art machine learning training, posing a grand challenge for real-time machine learning (RTML) at the edge. This goal of this project is to foster a systematic breakthrough in achieving efficient online training of state-of-the-art machine learning algorithms in pervasive resource-constrained platforms and applications. An order of magnitude advance in RTML would enable numerous edge devices to proactively interpret and learn from new data, improve their own performance using what they have learned, and adapt to dynamic environments, all in real time. Success in this project will enable truly intelligent edge devices to penetrate all walks of life and thus generate significant impacts on societies and economies. This project will lead to new courses and open-education resources that can attract diverse groups of students and eventually deliver a platform for inclusion and innovation. The project addresses the RTML grand challenge using a three-pronged 'co-design' approach that seamlessly integrates algorithm, architecture, and circuit-level innovations. Specifically, at the algorithm level, an efficient training framework for RTML, for which trained models are also natively efficient for inference, will be established. Aggressive time and energy reductions can be achieved, at first by improving general training techniques, and then by focusing particularly on online learning and adaptation. At the architecture level, the project will first target reducing the high cost of data movement by trading it for lower-cost computation, and then generate optimal dataflows and hardware architectures to maximize the joint benefits of algorithms and hardware. At the circuit level, the project will leverage adaptive low-precision algorithms and architectures to design ultra-energy-efficient mixed-signal compute fabrics. Statistical computing techniques will be incorporated to demonstrate efficient, scalable, and robust machine learning chips. Finally, at the system level, an integration effort will be included to aid the realization of realistic system goals and to evaluate the innovations of the three core thrusts.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.
机器学习的最新进展正在推动对智能物联网(IoT)的需求不断增长,即,边缘网络应用。其中许多,如自动驾驶汽车,机器人和医疗可穿戴设备,需要实时和原位学习才能被视为真正的智能。然而,在边缘设备处可用的有限计算和能量资源(例如,移动的设备、传感器)与最先进的机器学习训练的巨大且不断增长的成本不一致,这对边缘的实时机器学习(RTML)构成了巨大的挑战。该项目的目标是在普遍的资源受限平台和应用程序中实现最先进的机器学习算法的有效在线训练方面取得系统性突破。RTML的一个数量级的进步将使许多边缘设备能够主动解释和学习新数据,使用它们所学到的知识提高自己的性能,并适应动态环境,所有这些都是真实的时间。该项目的成功将使真正的智能边缘设备渗透到各行各业,从而对社会和经济产生重大影响。该项目将带来新的课程和开放教育资源,可以吸引不同的学生群体,并最终提供一个包容和创新的平台。 该项目使用三管齐下的“协同设计”方法解决了RTML的重大挑战,该方法无缝集成了算法、架构和电路级创新。具体而言,在算法层面,将建立一个有效的RTML训练框架,训练模型也是天生有效的推理。可以通过改进一般培训技术,然后特别关注在线学习和适应,来大幅减少时间和精力。在架构层面,该项目将首先以降低数据移动的高成本为目标,将其转换为低成本计算,然后生成最佳的硬件架构和硬件架构,以最大限度地提高算法和硬件的联合效益。在电路层面,该项目将利用自适应低精度算法和架构来设计超节能混合信号计算结构。将采用统计计算技术来展示高效、可扩展和强大的机器学习芯片。最后,在系统层面,将包括一个集成的努力,以帮助实现现实的系统目标,并评估三个核心thrusts.This奖项的创新反映了NSF的法定使命,并已被认为是值得的支持,通过评估使用基金会的智力价值和更广泛的影响审查标准。

项目成果

期刊论文数量(21)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference
CPT: Efficient Deep Neural Network Training via Cyclic Precision
  • DOI:
  • 发表时间:
    2021-01
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Y. Fu;Han Guo;Meng Li;Xin Yang;Yining Ding;V. Chandra;Yingyan Lin
  • 通讯作者:
    Y. Fu;Han Guo;Meng Li;Xin Yang;Yining Ding;V. Chandra;Yingyan Lin
ERSAM: Neural Architecture Search for Energy-Efficient and Real-Time Social Ambiance Measurement
E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings
  • DOI:
  • 发表时间:
    2019-10
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Yue Wang;Ziyu Jiang;Xiaohan Chen;Pengfei Xu;Yang Zhao;Yingyan Lin;Zhangyang Wang
  • 通讯作者:
    Yue Wang;Ziyu Jiang;Xiaohan Chen;Pengfei Xu;Yang Zhao;Yingyan Lin;Zhangyang Wang
AutoDNNchip: An Automated DNN Chip Predictor and Builder for Both FPGAs and ASICs
{{ 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 }}

Yingyan Lin其他文献

NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations
NeRFool:揭示可推广神经辐射场对抗对抗性扰动的脆弱性
Instant-NeRF: Instant On-Device Neural Radiance Field Training via Algorithm-Accelerator Co-Designed Near-Memory Processing
Instant-NeRF:通过算法加速器共同设计的近内存处理进行即时设备上神经辐射现场训练
  • DOI:
    10.1109/dac56929.2023.10247710
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Yang Zhao;Shang Wu;Jingqun Zhang;Sixu Li;Chaojian Li;Yingyan Lin
  • 通讯作者:
    Yingyan Lin
Performance Analysis of Direct Carbon Fuel Cell-Braysson Heat Engine Coupling System
直接碳燃料电池-布雷松热机耦合系统性能分析
Performance Multiple Objective Optimization of Irreversible Direct Carbon Fuel Cell/Stirling Thermo-Mechanical Coupling System
不可逆直接碳燃料电池/斯特林热机耦合系统性能多目标优化
NetBooster: Empowering Tiny Deep Learning By Standing on the Shoulders of Deep Giants
NetBooster:站在深度巨人的肩膀上,为微小的深度学习赋能
  • DOI:
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Zhongzhi Yu;Y. Fu;Jiayi Yuan;Haoran You;Yingyan Lin
  • 通讯作者:
    Yingyan Lin

Yingyan Lin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('Yingyan Lin', 18)}}的其他基金

RTML: Large: Collaborative: Harmonizing Predictive Algorithms and Mixed-Signal/Precision Circuits via Computation-Data Access Exchange and Adaptive Dataflows
RTML:大型:协作:通过计算数据访问交换和自适应数据流协调预测算法和混合信号/精密电路
  • 批准号:
    2400511
  • 财政年份:
    2023
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Standard Grant
CAREER: Differentiable Network-Accelerator Co-Search Towards Ubiquitous On-Device Intelligence and Green AI
职业生涯:可微分网络加速器联合搜索,实现无处不在的设备智能和绿色人工智能
  • 批准号:
    2345577
  • 财政年份:
    2023
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Continuing Grant
SHF: Medium: Cross-Stack Algorithm-Hardware-Systems Optimization Towards Ubiquitous On-Device 3D Intelligence
SHF:中:跨堆栈算法-硬件-系统优化,实现无处不在的设备上 3D 智能
  • 批准号:
    2312758
  • 财政年份:
    2023
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Continuing Grant
Collaborative Research: Enabling Intelligent Cameras in Internet-of-Things via a Holistic Platform, Algorithm, and Hardware Co-design
协作研究:通过整体平台、算法和硬件协同设计实现物联网中的智能相机
  • 批准号:
    2346091
  • 财政年份:
    2023
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Standard Grant
SHF: Medium:DILSE: Codesigning Decentralized Incremental Learning System via Streaming Data Summarization on Edge
SHF:Medium:DILSE:通过边缘流数据汇总共同设计去中心化增量学习系统
  • 批准号:
    2211815
  • 财政年份:
    2022
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Continuing Grant
CAREER: Differentiable Network-Accelerator Co-Search Towards Ubiquitous On-Device Intelligence and Green AI
职业生涯:可微分网络加速器联合搜索,实现无处不在的设备智能和绿色人工智能
  • 批准号:
    2048183
  • 财政年份:
    2021
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Continuing Grant
NSF Workshop: Machine Learning Hardware Breakthroughs Towards Green AI and Ubiquitous On-Device Intelligence. To be Held in November 2020.
NSF 研讨会:机器学习硬件突破绿色人工智能和无处不在的设备智能。
  • 批准号:
    2054865
  • 财政年份:
    2020
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Standard Grant
CCRI: Medium: Collaborative Research: 3DML: A Platform for Data, Design and Deployed Validation of Machine Learning for Wireless Networks and Mobile Applications
CCRI:媒介:协作研究:3DML:无线网络和移动应用机器学习的数据、设计和部署验证平台
  • 批准号:
    2016727
  • 财政年份:
    2020
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Standard Grant
Collaborative Research: Enabling Intelligent Cameras in Internet-of-Things via a Holistic Platform, Algorithm, and Hardware Co-design
协作研究:通过整体平台、算法和硬件协同设计实现物联网中的智能相机
  • 批准号:
    1934767
  • 财政年份:
    2019
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Standard Grant

相似国自然基金

水稻穗粒数调控关键因子LARGE6的分子遗传网络解析
  • 批准号:
  • 批准年份:
    2022
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目
量子自旋液体中拓扑拟粒子的性质:量子蒙特卡罗和新的large-N理论
  • 批准号:
  • 批准年份:
    2020
  • 资助金额:
    62 万元
  • 项目类别:
    面上项目
甘蓝型油菜Large Grain基因调控粒重的分子机制研究
  • 批准号:
    31972875
  • 批准年份:
    2019
  • 资助金额:
    58.0 万元
  • 项目类别:
    面上项目
Large PB/PB小鼠 视网膜新生血管模型的研究
  • 批准号:
    30971650
  • 批准年份:
    2009
  • 资助金额:
    8.0 万元
  • 项目类别:
    面上项目
基因discs large在果蝇卵母细胞的后端定位及其体轴极性形成中的作用机制
  • 批准号:
    30800648
  • 批准年份:
    2008
  • 资助金额:
    20.0 万元
  • 项目类别:
    青年科学基金项目
LARGE基因对口腔癌细胞中α-DG糖基化及表达的分子调控
  • 批准号:
    30772435
  • 批准年份:
    2007
  • 资助金额:
    29.0 万元
  • 项目类别:
    面上项目

相似海外基金

Collaborative Research: Conference: Large Language Models for Biological Discoveries (LLMs4Bio)
合作研究:会议:生物发现的大型语言模型 (LLMs4Bio)
  • 批准号:
    2411529
  • 财政年份:
    2024
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Standard Grant
Collaborative Research: Conference: Large Language Models for Biological Discoveries (LLMs4Bio)
合作研究:会议:生物发现的大型语言模型 (LLMs4Bio)
  • 批准号:
    2411530
  • 财政年份:
    2024
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Standard Grant
Collaborative Research: Using Polarimetric Radar Observations, Cloud Modeling, and In Situ Aircraft Measurements for Large Hail Detection and Warning of Impending Hail
合作研究:利用偏振雷达观测、云建模和现场飞机测量来检测大冰雹并预警即将发生的冰雹
  • 批准号:
    2344259
  • 财政年份:
    2024
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Standard Grant
Collaborative Research: OAC Core: Distributed Graph Learning Cyberinfrastructure for Large-scale Spatiotemporal Prediction
合作研究:OAC Core:用于大规模时空预测的分布式图学习网络基础设施
  • 批准号:
    2403312
  • 财政年份:
    2024
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Standard Grant
Collaborative Research: NSFGEO/NERC: After the cataclysm: cryptic degassing and delayed recovery in the wake of Large Igneous Province volcanism
合作研究:NSFGEO/NERC:灾难之后:大型火成岩省火山活动后的神秘脱气和延迟恢复
  • 批准号:
    2317936
  • 财政年份:
    2024
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Continuing Grant
Collaborative Research: Large-Scale Wireless RF Networks of Microchip Sensors
合作研究:微芯片传感器的大规模无线射频网络
  • 批准号:
    2322601
  • 财政年份:
    2024
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Standard Grant
Collaborative Research: NSFGEO/NERC: After the cataclysm: cryptic degassing and delayed recovery in the wake of Large Igneous Province volcanism
合作研究:NSFGEO/NERC:灾难之后:大型火成岩省火山活动后的神秘脱气和延迟恢复
  • 批准号:
    2317938
  • 财政年份:
    2024
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Continuing Grant
Collaborative Research: SHF: Medium: Enabling Graphics Processing Unit Performance Simulation for Large-Scale Workloads with Lightweight Simulation Methods
合作研究:SHF:中:通过轻量级仿真方法实现大规模工作负载的图形处理单元性能仿真
  • 批准号:
    2402804
  • 财政年份:
    2024
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Standard Grant
Collaborative Research: Using Polarimetric Radar Observations, Cloud Modeling, and In Situ Aircraft Measurements for Large Hail Detection and Warning of Impending Hail
合作研究:利用偏振雷达观测、云建模和现场飞机测量来检测大冰雹并预警即将发生的冰雹
  • 批准号:
    2344260
  • 财政年份:
    2024
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Standard Grant
Collaborative Research: Scalable Manufacturing of Large-Area Thin Films of Metal-Organic Frameworks for Separations Applications
合作研究:用于分离应用的大面积金属有机框架薄膜的可扩展制造
  • 批准号:
    2326714
  • 财政年份:
    2024
  • 资助金额:
    $ 58.53万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了