SHF: Small: Fast Sign-Off of Machine Learning Systems: From Circuit-Level Modeling to Statistical System Validation
SHF:小型:机器学习系统的快速签核:从电路级建模到统计系统验证
基本信息
- 批准号:1813567
- 负责人:
- 金额:$ 40万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2018
- 资助国家:美国
- 起止时间:2018-10-01 至 2022-09-30
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Machine learning has been adopted by a broad range of emerging applications, including health monitoring, autonomous driving, advanced manufacturing, etc. However, any machine learning system cannot be 100% accurate due to the accuracy limitation posed by machine learning algorithms and the circuit-level non-ideal features associated with its hardware implementation. This project investigates a radically new framework for efficient validation of machine learning systems implemented with nano-scale integrated circuits. It aims to identify and synthesize the critical corner cases for which a machine learning system is likely to fail. The project is expected to initialize a paradigm shift in today's design methodology for complex machine learning systems, thereby leading to an immediate impact on a broad range of industrial sectors relying on machine intelligence. In addition, the proposed education activities create a large number of unique training opportunities for both academic and industrial participants, substantially improving the education infrastructure and generate high-quality researchers and practitioners for the society. Today, validating a machine learning system with high throughout, low power and complex functionality is an extremely challenging task. This project attacks the grand challenge by developing a novel validation framework composed of two major components: (1) corner-case generation and (2) rare-failure rate estimation. Both physical circuit models and statistical generative models are proposed to synthesize a large amount of test cases, reducing the experimental cost to physically record the corner-cases that are difficult to observe. Furthermore, a novel formulation, based on subset partition and graph embedding, is developed to efficiently inspect the likely-failed test cases and consequently estimate the rare- failure rate that is expensive to capture by random sampling. Built upon these mathematical tools, the project's framework offers a fundamental infrastructure that could facilitate radical breakthroughs over numerous machine learning applications.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.
机器学习已被广泛的新兴应用程序所采用,包括健康监控,自动驾驶,高级制造等。但是,由于机器学习算法和电路 - 级别的非理想功能与其硬件实现相关。该项目研究了一个彻底的新框架,用于有效验证使用纳米级集成电路实施的机器学习系统。它旨在识别和综合机器学习系统可能失败的关键角案例。预计该项目将在当今的复杂机器学习系统的当今设计方法中初始化范式转变,从而导致对依靠机器智能的广泛工业部门产生直接影响。此外,拟议的教育活动为学术和工业参与者创造了大量独特的培训机会,从而大大改善了教育基础设施,并为社会造就了高质量的研究人员和从业人员。如今,验证整个,低功率和复杂功能的机器学习系统是一项极具挑战性的任务。该项目通过开发一个由两个主要组成部分组成的新颖验证框架来攻击巨大的挑战:(1)角案例产生和(2)稀有失败率估计。提出了物理电路模型和统计生成模型,以综合大量的测试用例,从而降低了实验成本,以便物理记录难以观察的角案箱。此外,开发了一种基于子集分区和图形嵌入的新型配方,以有效地检查可能发生的测试案例,因此估计了通过随机抽样捕获的罕见失败率。该项目的框架建立在这些数学工具的基础上,提供了一个基本的基础设施,可以促进对众多机器学习应用的激进突破。该奖项反映了NSF的法定任务,并被认为是值得通过基金会的知识分子优点和更广泛影响的评估标准通过评估来进行评估的。
项目成果
期刊论文数量(3)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Unsupervised Root-Cause Analysis with Transfer Learning for Integrated Systems
通过集成系统的迁移学习进行无监督根本原因分析
- DOI:10.1109/vts50974.2021.9441030
- 发表时间:2021
- 期刊:
- 影响因子:0
- 作者:Pan, Renjian;Li, Xin;Chakrabarty, Krishnendu
- 通讯作者:Chakrabarty, Krishnendu
Semi-Supervised Root-Cause Analysis with Co-Training for Integrated Systems
集成系统协同训练的半监督根本原因分析
- DOI:10.1109/vts52500.2021.9794192
- 发表时间:2022
- 期刊:
- 影响因子:0
- 作者:Pan, Renjian;Li, Xin;Chakrabarty, Krishnendu
- 通讯作者:Chakrabarty, Krishnendu
Intelligent corner synthesis via cycle-consistent generative adversarial networks for efficient validation of autonomous driving systems
- DOI:10.1109/aspdac.2018.8297275
- 发表时间:2018-01
- 期刊:
- 影响因子:0
- 作者:Handi Yu;Xin Li
- 通讯作者:Handi Yu;Xin Li
{{
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 }}
Kishor Trivedi其他文献
DASON: Dependability Assessment Framework for Imperfect Distributed SDN Implementations
DASON:不完美的分布式 SDN 实施的可靠性评估框架
- DOI:
10.1109/tnsm.2020.2973925 - 发表时间:
2020-06 - 期刊:
- 影响因子:5.3
- 作者:
Petra Vizarreta;Kishor Trivedi;Veena Mendiratta;Wolfgang Kellerer;Carmen Mas-Machuca - 通讯作者:
Carmen Mas-Machuca
Kishor Trivedi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('Kishor Trivedi', 18)}}的其他基金
TWC: TTP Option: Small: Collaborative: SRN: On Establishing Secure and Resilient Networking Services
TWC:TTP 选项:小型:协作:SRN:关于建立安全和弹性的网络服务
- 批准号:
1523994 - 财政年份:2015
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
NeTS: Small: Collaborative Research: Analytic Modeling and Enhancement of Vehicular Ad Hoc Networks for Safety Related Applications
NeTS:小型:协作研究:用于安全相关应用的车辆自组织网络的分析建模和增强
- 批准号:
1017722 - 财政年份:2010
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
Collaborative Research: CT-ER MiMANSaS: Metrics, Models and Analysis of Network Security and Survivability
合作研究:CT-ER MiMANSaS:网络安全和生存能力的指标、模型和分析
- 批准号:
0831325 - 财政年份:2008
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
Collaborative Project: NSF Partnership in the Center for Advanced Computing and Communication
合作项目:美国国家科学基金会 (NSF) 高级计算和通信中心合作伙伴关系
- 批准号:
9980591 - 财政年份:1999
- 资助金额:
$ 40万 - 项目类别:
Continuing Grant
US-Italy Cooperative Research: Dependability Modeling and Analysis of Phased-Mission Systems
美意合作研究:分阶段任务系统的可靠性建模和分析
- 批准号:
9972009 - 财政年份:1999
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
U.S.-Korea Cooperative Research on Performance Analysis Methodology for the Future Wireless Communicatin Systems
美韩合作研究未来无线通信系统性能分析方法
- 批准号:
9727221 - 财政年份:1998
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
Challenges in CISE: TUNE: System Support for Memory-Friendly Programming
CISE 中的挑战:TUNE:内存友好型编程的系统支持
- 批准号:
9726370 - 财政年份:1997
- 资助金额:
$ 40万 - 项目类别:
Continuing Grant
I/UCRC for Advanced Computing and Communication: Architecture-Based Estimation of Software Reliability
用于高级计算和通信的 I/UCRC:基于体系结构的软件可靠性估计
- 批准号:
9714965 - 财政年份:1997
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
Industry/University Cooperative Research Center for Advanced Computing and Communication
先进计算与通信产学合作研究中心
- 批准号:
9418765 - 财政年份:1994
- 资助金额:
$ 40万 - 项目类别:
Continuing Grant
I/UCRC for Computer Engineering System Center, A Planning Grant Proposal
I/UCRC 计算机工程系统中心规划拨款提案
- 批准号:
9312908 - 财政年份:1993
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
相似国自然基金
单细胞分辨率下的石杉碱甲介导小胶质细胞极化表型抗缺血性脑卒中的机制研究
- 批准号:82304883
- 批准年份:2023
- 资助金额:30 万元
- 项目类别:青年科学基金项目
小分子无半胱氨酸蛋白调控生防真菌杀虫活性的作用与机理
- 批准号:32372613
- 批准年份:2023
- 资助金额:50 万元
- 项目类别:面上项目
诊疗一体化PS-Hc@MB协同训练介导脑小血管病康复的作用及机制研究
- 批准号:82372561
- 批准年份:2023
- 资助金额:49 万元
- 项目类别:面上项目
非小细胞肺癌MECOM/HBB通路介导血红素代谢异常并抑制肿瘤起始细胞铁死亡的机制研究
- 批准号:82373082
- 批准年份:2023
- 资助金额:49 万元
- 项目类别:面上项目
FATP2/HILPDA/SLC7A11轴介导肿瘤相关中性粒细胞脂代谢重编程影响非小细胞肺癌放疗免疫的作用和机制研究
- 批准号:82373304
- 批准年份:2023
- 资助金额:49 万元
- 项目类别:面上项目
相似海外基金
SHF:Small: Learning-based Fast Analysis and Fixing for Electromigration Damage
SHF:Small:基于学习的电迁移损伤快速分析和修复
- 批准号:
2305437 - 财政年份:2023
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
SHF:Small: Machine Learning Approach for Fast Electromigration Analysis and Full-Chip Assessment
SHF:Small:用于快速电迁移分析和全芯片评估的机器学习方法
- 批准号:
2007135 - 财政年份:2020
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
SHF: Small: THz surface Wave Based Interconnect Technology for Ultra-fast Data Transfer
SHF:小型:基于太赫兹表面波的互连技术,用于超快速数据传输
- 批准号:
1909937 - 财政年份:2019
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
SHF: Small: Indy: Toward Safe and Fast Compiler Flags
SHF:小:Indy:迈向安全快速的编译器标志
- 批准号:
1817073 - 财政年份:2018
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
SHF: Small: A reconfigurable architecture for digital circuit computation by fast, robust, and leakless DNA strand displacement cascades
SHF:小型:通过快速、稳健且无泄漏的 DNA 链位移级联进行数字电路计算的可重构架构
- 批准号:
1718938 - 财政年份:2017
- 资助金额:
$ 40万 - 项目类别:
Standard Grant