SHF: Medium: A Cloudless Universal Translator
SHF:Medium:无云通用翻译器
基本信息
- 批准号:1704834
- 负责人:
- 金额:$ 100万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2017
- 资助国家:美国
- 起止时间:2017-06-01 至 2025-03-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
This project explores the research foundations necessary to build a universal language translator on a portable computing device for secure private use without the need for reliance on cloud servers. Transformative developments in both machine learning and computer hardware design have made this exciting challenge feasible. The project will nurture a true bidirectional co-design process between researchers in both fields. The broader impacts of the project include: 1) the practical applications of widely available language translation technology, and 2) the training of graduate engineers who have specialization in machine learning as well as hardware and circuit design, skills in broad demand in US industry.The problem of developing hardware to fit deep learning models is not simply one of fitting current machine learning models on current circuit technology, as the models are much too large, too slow, and too energy-hungry. This project will need to develop novel machine learning techniques that take these factors into account. Machine learning researchers mostly optimize for accuracy; however, the project goal will require considering trade-offs on model size, speed, and computation. Conversely, the hardware design will have to consider and exploit the unique properties of the neural models, such as high-tolerance to certain types of noise, repeated computational structure, and non-linear interactions. The research approach includes three major areas for interaction: model compression, approximation in architecture, and training for unreliable hardware. Succeeding in these goals will be necessary to build a successful on-device system.
该项目探讨了在便携式计算设备上构建通用语言翻译器所需的研究基础,以供安全的私人使用,而无需依赖云服务器。机器学习和计算机硬件设计的变革性发展使这一令人兴奋的挑战变得可行。该项目将在这两个领域的研究人员之间培养一个真正的双向共同设计过程。该项目的广泛影响包括:1)广泛可用的语言翻译技术的实际应用,以及2)具有机器学习以及硬件和电路设计专业化的研究生工程师的培训,这些技能在美国工业中具有广泛的需求。开发硬件以适应深度学习模型的问题不仅仅是将当前的机器学习模型与当前的电路技术相匹配,因为模型太大、太慢、太耗能。该项目将需要开发新的机器学习技术,将这些因素考虑在内。机器学习研究人员主要针对准确性进行优化;然而,项目目标将需要考虑模型大小,速度和计算的权衡。相反,硬件设计将不得不考虑和利用神经模型的独特属性,例如对某些类型的噪声的高容忍度,重复的计算结构和非线性相互作用。研究方法包括三个主要领域的互动:模型压缩,近似的架构,和训练不可靠的硬件。成功实现这些目标对于构建成功的设备上系统是必要的。
项目成果
期刊论文数量(9)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
FlexACC: A Programmable Accelerator with Application-Specific ISA for Flexible Deep Neural Network Inference
FlexACC:具有特定于应用的 ISA 的可编程加速器,用于灵活的深度神经网络推理
- DOI:10.1109/asap52443.2021.00046
- 发表时间:2021
- 期刊:
- 影响因子:0
- 作者:Yang, En-Yu;Jia, Tianyu;Brooks, David;Wei, Gu-Yeon
- 通讯作者:Wei, Gu-Yeon
EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference
- DOI:10.1145/3466752.3480095
- 发表时间:2020-11
- 期刊:
- 影响因子:0
- 作者:Thierry Tambe;Coleman Hooper;Lillian Pentecost;Tianyu Jia;En-Yu Yang;M. Donato;Victor Sanh;P. Whatmough;Alexander M. Rush;D. Brooks;Gu-Yeon Wei
- 通讯作者:Thierry Tambe;Coleman Hooper;Lillian Pentecost;Tianyu Jia;En-Yu Yang;M. Donato;Victor Sanh;P. Whatmough;Alexander M. Rush;D. Brooks;Gu-Yeon Wei
Latent Alignment and Variational Attention
- DOI:
- 发表时间:2018-07
- 期刊:
- 影响因子:0
- 作者:Yuntian Deng;Yoon Kim;Justin T Chiu;Demi Guo;Alexander M. Rush
- 通讯作者:Yuntian Deng;Yoon Kim;Justin T Chiu;Demi Guo;Alexander M. Rush
MASR: A Modular Accelerator for Sparse RNNs
- DOI:10.1109/pact.2019.00009
- 发表时间:2019-08
- 期刊:
- 影响因子:0
- 作者:Udit Gupta;Brandon Reagen;Lillian Pentecost;M. Donato;Thierry Tambe;Alexander M. Rush;Gu-Yeon Wei;D. Brooks
- 通讯作者:Udit Gupta;Brandon Reagen;Lillian Pentecost;M. Donato;Thierry Tambe;Alexander M. Rush;Gu-Yeon Wei;D. Brooks
Latent Normalizing Flows for Discrete Sequences
- DOI:
- 发表时间:2019-01
- 期刊:
- 影响因子:0
- 作者:Zachary M. Ziegler;Alexander M. Rush
- 通讯作者:Zachary M. Ziegler;Alexander M. Rush
{{
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 }}
David Brooks其他文献
The VPH-Physiome Project: Standards, tools and databases for multi-scale physiological modelling
VPH-Physiome 项目:多尺度生理建模的标准、工具和数据库
- DOI:
10.1007/978-88-470-1935-5_8 - 发表时间:
2012 - 期刊:
- 影响因子:3.8
- 作者:
P. Hunter;C. Bradley;Randall Britten;David Brooks;L. Carotenuto;Richard Christie;Alejandro F Frangi;A. Garny;David Ladd;C. Little;D. Nickerson;P. Nielsen;Andrew L. Miller;X. Planes;Martin Steghoffer;A. Young;Tommy Yu - 通讯作者:
Tommy Yu
Carbon Dependencies in Datacenter Design and Management
数据中心设计和管理中的碳依赖性
- DOI:
- 发表时间:
2023 - 期刊:
- 影响因子:0
- 作者:
Bilge Acun;Benjamin Lee;Fiodar Kazhamiaka;Aditya Sundarrajan;Kiwan Maeng;Manoj Chakkaravarthy;David Brooks;Carole - 通讯作者:
Carole
Immune profiling of advanced, recurrent metastatic endometrial cancer using high-dimensional time-of-flight mass cytometry (CyTOF)
- DOI:
10.1016/s0090-8258(21)00972-0 - 发表时间:
2021-08-01 - 期刊:
- 影响因子:
- 作者:
Ramy Gadalla;Ben Wang;David Brooks;Daniela Matei;Panagiotis Konstantinopoulos;Matthew Block;Andrea Jewell;Stephanie Gaillard;Michael McHale;Carolyn McCourt;Eugenia Girda;Floor Backes;Theresa Werner;Linda Duska;Siobhan Kehoe;Ilaria Colombo;Rachel Wildman;John Wright;Gini Fleming;Pamela Ohashi - 通讯作者:
Pamela Ohashi
Abortive keratoacanthoma: a hitherto unrecognised variant
- DOI:
10.3109/00313025.2010.522176 - 发表时间:
2010-12-01 - 期刊:
- 影响因子:
- 作者:
David Weedon;David Brooks;Jonathan Malo;Richard Williamson - 通讯作者:
Richard Williamson
Statistical study of UV spectral properties in flares using the multi-wavelength observations by IRIS, Hinode, SDO, and RHESSI
利用 IRIS、Hinode、SDO 和 RHESSI 的多波长观测对耀斑的紫外光谱特性进行统计研究
- DOI:
- 发表时间:
2018 - 期刊:
- 影响因子:0
- 作者:
Kyoung SUN Lee;Kyoko Watanabe;Hirohisa Hara;David Brooks;Shinsuke Imada - 通讯作者:
Shinsuke Imada
David Brooks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('David Brooks', 18)}}的其他基金
Collaborative Research:PPoSS:Planning: Streamware - A Scalable Framework for Accelerating Streaming Data Science
合作研究:PPoSS:规划:Streamware - 加速流数据科学的可扩展框架
- 批准号:
2118985 - 财政年份:2021
- 资助金额:
$ 100万 - 项目类别:
Standard Grant
CSR: SMALL: Virtualized Accelerators for Scalable, Composable Architectures
CSR:小型:用于可扩展、可组合架构的虚拟化加速器
- 批准号:
1718160 - 财政年份:2017
- 资助金额:
$ 100万 - 项目类别:
Standard Grant
SHF: Small: Exploration of energy-optimized computing architectures using integrated voltage regulators
SHF:小型:使用集成稳压器探索能源优化计算架构
- 批准号:
1218298 - 财政年份:2012
- 资助金额:
$ 100万 - 项目类别:
Standard Grant
Collaborative Research: II-NEW: Prototyping Platform to Enable Power-Centric Multicore Research
协作研究:II-NEW:支持以功耗为中心的多核研究的原型设计平台
- 批准号:
1059264 - 财政年份:2011
- 资助金额:
$ 100万 - 项目类别:
Standard Grant
Workshop to Define Student Collaborative Climate Science Research; Silver Spring, MD
定义学生协作气候科学研究的研讨会;
- 批准号:
1000357 - 财政年份:2010
- 资助金额:
$ 100万 - 项目类别:
Standard Grant
Travel Support for the 2010 IEEE International Symposium on Performance Analysis of Systems and Software
2010 年 IEEE 国际系统和软件性能分析研讨会的差旅支持
- 批准号:
0963160 - 财政年份:2009
- 资助金额:
$ 100万 - 项目类别:
Standard Grant
NSF CCF-CPA: Reliability in the Face of Variability under Nanoscale Technology Scaling
NSF CCF-CPA:纳米技术扩展下面对可变性的可靠性
- 批准号:
0702344 - 财政年份:2007
- 资助金额:
$ 100万 - 项目类别:
Continuing Grant
COLLABORATIVE RESEARCH -- CSR-EHS: Integrated Power Delivery - Hardware-Software Techniques to Eliminate Off-Chip Regulation from Embedded Systems
合作研究——CSR-EHS:集成供电——消除嵌入式系统片外调节的硬件-软件技术
- 批准号:
0720566 - 财政年份:2007
- 资助金额:
$ 100万 - 项目类别:
Continuing Grant
CAREER: A Framework for Early-Stage Computer Architecture Design Space Exploration and Optimization
职业:早期计算机架构设计空间探索和优化的框架
- 批准号:
0448313 - 财政年份:2005
- 资助金额:
$ 100万 - 项目类别:
Continuing Grant
相似海外基金
Collaborative Research: CyberTraining: Implementation: Medium: Training Users, Developers, and Instructors at the Chemistry/Physics/Materials Science Interface
协作研究:网络培训:实施:媒介:在化学/物理/材料科学界面培训用户、开发人员和讲师
- 批准号:
2321102 - 财政年份:2024
- 资助金额:
$ 100万 - 项目类别:
Standard Grant
RII Track-4:@NASA: Bluer and Hotter: From Ultraviolet to X-ray Diagnostics of the Circumgalactic Medium
RII Track-4:@NASA:更蓝更热:从紫外到 X 射线对环绕银河系介质的诊断
- 批准号:
2327438 - 财政年份:2024
- 资助金额:
$ 100万 - 项目类别:
Standard Grant
Collaborative Research: Topological Defects and Dynamic Motion of Symmetry-breaking Tadpole Particles in Liquid Crystal Medium
合作研究:液晶介质中对称破缺蝌蚪粒子的拓扑缺陷与动态运动
- 批准号:
2344489 - 财政年份:2024
- 资助金额:
$ 100万 - 项目类别:
Standard Grant
Collaborative Research: AF: Medium: The Communication Cost of Distributed Computation
合作研究:AF:媒介:分布式计算的通信成本
- 批准号:
2402836 - 财政年份:2024
- 资助金额:
$ 100万 - 项目类别:
Continuing Grant
Collaborative Research: AF: Medium: Foundations of Oblivious Reconfigurable Networks
合作研究:AF:媒介:遗忘可重构网络的基础
- 批准号:
2402851 - 财政年份:2024
- 资助金额:
$ 100万 - 项目类别:
Continuing Grant
Collaborative Research: CIF: Medium: Snapshot Computational Imaging with Metaoptics
合作研究:CIF:Medium:Metaoptics 快照计算成像
- 批准号:
2403122 - 财政年份:2024
- 资助金额:
$ 100万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Differentiable Hardware Synthesis
合作研究:SHF:媒介:可微分硬件合成
- 批准号:
2403134 - 财政年份:2024
- 资助金额:
$ 100万 - 项目类别:
Standard 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:
$ 100万 - 项目类别:
Standard Grant
Collaborative Research: CIF-Medium: Privacy-preserving Machine Learning on Graphs
合作研究:CIF-Medium:图上的隐私保护机器学习
- 批准号:
2402815 - 财政年份:2024
- 资助金额:
$ 100万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Tiny Chiplets for Big AI: A Reconfigurable-On-Package System
合作研究:SHF:中:用于大人工智能的微型芯片:可重新配置的封装系统
- 批准号:
2403408 - 财政年份:2024
- 资助金额:
$ 100万 - 项目类别:
Standard Grant