III: Medium: Collaborative Research: MUDL: Multidimensional Uncertainty-Aware Deep Learning Framework

III:媒介:协作研究:MUDL:多维不确定性感知深度学习框架

基本信息

  • 批准号:
    2107449
  • 负责人:
  • 金额:
    $ 50万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2021
  • 资助国家:
    美国
  • 起止时间:
    2021-10-01 至 2025-09-30
  • 项目状态:
    未结题

项目摘要

People encounter serious hurdles in finding effective decision-making solutions to real world problems because of uncertainty from a lack of information, conflicting information, and/or unsure observations. Critical safety concerns have been consistently highlighted because how to interpret this uncertainty has not been carefully investigated. If the uncertainty is misinterpreted, this can result in unnecessary risk. For example, a self-driving autonomous car can misdetect a human in the road. An artificial intelligence-based medical assistant may misdiagnose cancer as a benign tumor. Further, a phishing email can be detected as a normal email. The consequences of all these misdetections or misclassifications caused by different types of uncertainty adds risk and potential adverse events. Artificial intelligence (AI) researchers have actively explored how to solve various decision-making problems under uncertainty. However, no prior research has looked into how different approaches of studying uncertainty in AI can leverage each other. This project studies how to measure different causes of uncertainty and use them to solve diverse decision-making problems more effectively. This project can help develop trustworthy AI algorithms that can be used in many real world decision-making problems. In addition, this project is highly transdisciplinary so that it can encourage broader, newer, and more diverse approaches. To magnify the impact of this project in research and education, this project leverages multicultural, diversity, and STEM programs for students with diverse backgrounds and under-represented populations. This project also includes seminar talks, workshops, short courses, and/or research projects for high school and community college students. This project aims to develop a suite of deep learning (DL) techniques by considering multiple types of uncertainties caused by different root causes and employ them to maximize the effectiveness of decision-making in the presence of highly intelligent, adversarial attacks. This project makes a synergistic but transformative research effort to study: (1) how different types of uncertainties can be quantified based on belief theory; (2) how the estimates of different types of uncertainties can be considered in DL-based approaches; and (3) how multiple types of uncertainties influence the effectiveness and efficiency of decision-making in high-dimensional, complex problems. This project advances the state-of-the-art research by performing the following: (1) Proposing a scalable, robust unified DL-based framework to effectively infer predictive multidimensional uncertainty caused by heterogeneous root causes in adversarial environments. (2) Dealing with multidimensional uncertainty based on neural networks. (3) Enhancing both decision effectiveness and efficiency by considering multidimensional uncertainty-aware designs. (4) Testing proposed approaches to ensure their robustness in the presence of intelligent adversarial attackers with advanced deception tactics based on both simulation models and visualization tools.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.
由于缺乏信息,相互矛盾的信息和/或不确定的观察结果,人们在寻找有效的决策解决方案时遇到了严重的障碍。 始终强调了关键的安全问题,因为如何解释这种不确定性尚未仔细研究。如果误解了不确定性,则可能导致不必要的风险。例如,自动驾驶的自动驾驶汽车可能会在路上误导人类。基于人工智能的医疗助理可能会误诊癌症作为良性肿瘤。 此外,可以将网络钓鱼电子邮件视为普通电子邮件。 由不同类型的不确定性引起的所有这些误导或错误分类的后果增加了风险和潜在的不良事件。 人工智能(AI)研究人员积极探索了如何在不确定性下解决各种决策问题。 但是,没有先前的研究研究了AI中研究不确定性的不同方法如何相互利用。 该项目研究了如何衡量不确定性的不同原因,并使用它们来更有效地解决各种决策问题。 该项目可以帮助开发可信赖的AI算法,这些算法可用于许多现实世界决策问题。此外,该项目是高度跨学科的,因此可以鼓励更广泛,更新和更多样化的方法。 为了扩大该项目在研究和教育中的影响,该项目利用多元文化,多样性和STEM计划为背景和代表性不足的学生提供了多元文化,多样性和STEM计划。该项目还包括研讨会,研讨会,短课程和/或高中和社区大学生的研究项目。 该项目旨在通过考虑由不同的根本原因引起的多种类型的不确定性来开发一套深度学习(DL)技术,并利用它们在存在高度聪明,对抗性攻击的情况下最大化决策的有效性。 该项目对研究进行了协同但变革性的研究工作:(1)如何根据信仰理论量化不同类型的不确定性; (2)如何在基于DL的方法中考虑不同类型的不确定性的估计; (3)多种类型的不确定性如何影响高维,复杂问题中决策的有效性和效率。该项目通过执行以下操作来推进最先进的研究:(1)提出一个可扩展的,可靠的统一基于DL的框架,以有效地推断出在对抗环境中由异构根本原因引起的预测性多维不确定性。 (2)基于神经网络处理多维不确定性。 (3)通过考虑多维不确定性意识设计来提高决策有效性和效率。 (4)测试提出的方法,以确保其在智能的对抗攻击者存在的情况下具有基于模拟模型和可视化工具的先进欺骗策略的智能攻击者。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审查标准来通过评估来通过评估来支持的。

项目成果

期刊论文数量(7)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Interactive Web-Based Visual Analysis on Network Traffic Data
基于交互式网络的网络流量数据可视化分析
  • DOI:
    10.3390/info14010016
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    3.1
  • 作者:
    Jeong, Dong Hyun;Cho, Jin-Hee;Chen, Feng;Kaplan, Lance;Jøsang, Audun;Ji, Soo-Yeon
  • 通讯作者:
    Ji, Soo-Yeon
A survey on uncertainty reasoning and quantification in belief theory and its application to deep learning
  • DOI:
    10.1016/j.inffus.2023.101987
  • 发表时间:
    2023-08
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Zhen Guo;Zelin Wan;Qisheng Zhang;Xujiang Zhao;Qi Zhang;L. Kaplan;A. Jøsang;Dong-Ho Jeong
  • 通讯作者:
    Zhen Guo;Zelin Wan;Qisheng Zhang;Xujiang Zhao;Qi Zhang;L. Kaplan;A. Jøsang;Dong-Ho Jeong
Multi-Label Temporal Evidential Neural Networks for Early Event Detection
Active Learning on Neural Networks through Interactive Generation of Digit Patterns and Visual Representation
  • DOI:
    10.1109/isec57711.2023.10402169
  • 发表时间:
    2023-03
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Dong H. Jeong;Jin-Hee Cho;Feng Chen;A. Jøsang;Soo-Yeon Ji
  • 通讯作者:
    Dong H. Jeong;Jin-Hee Cho;Feng Chen;A. Jøsang;Soo-Yeon Ji
How Out-of-Distribution Data Hurts Semi-Supervised Learning
  • DOI:
    10.1109/icdm54844.2022.00087
  • 发表时间:
    2020-10
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Xujiang Zhao;Killamsetty Krishnateja;Rishabh K. Iyer;Feng Chen
  • 通讯作者:
    Xujiang Zhao;Killamsetty Krishnateja;Rishabh K. Iyer;Feng Chen
{{ 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 }}

Feng Chen其他文献

Application of orthogonal fringe patterns in uniaxial microscopic 3D profilometry
正交条纹图案在单轴显微3D轮廓测量中的应用
  • DOI:
    10.1364/osac.409510
  • 发表时间:
    2020-11
  • 期刊:
  • 影响因子:
    1.6
  • 作者:
    Min Zhong;Ke Cheng;Feng Chen;Peng Duan;Min Li
  • 通讯作者:
    Min Li
A Formal Model Driven Approach to Dependable Software Evolution
可靠软件演化的形式化模型驱动方法
Parametric Analysis of the Drainage Performance of Porous Asphalt Pavement Based on a 3D FEM Method
基于3D有限元方法的多孔沥青路面排水性能参数分析
  • DOI:
    10.1061/(asce)mt.1943-5533.0003468
  • 发表时间:
    2020
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Tianjian Ji;Lei Xiao;Feng Chen
  • 通讯作者:
    Feng Chen
Computerized analysis of tongue sub-lingual veins to detect lung and breast cancers
计算机分析舌下静脉以检测肺癌和乳腺癌
Psychometric Evaluation of the Spiritual Perspective Scale in Palliative Care Nurses in China
中国姑息治疗护士精神视角量表的心理测量评估
  • DOI:
    10.1007/s10943-022-01582-w
  • 发表时间:
    2022
  • 期刊:
  • 影响因子:
    2.8
  • 作者:
    Feng Chen;Yi Zhang;Lingjun Zhou;Jing Cui
  • 通讯作者:
    Jing Cui

Feng Chen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('Feng Chen', 18)}}的其他基金

ATD: Sparse and Localized Graph Convolutional Networks for Anomaly Detection and Active Learning
ATD:用于异常检测和主动学习的稀疏和局部图卷积网络
  • 批准号:
    2220574
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
Collaborative Research: SHF: Medium: Hardware and Software Support for Memory-Centric Computing Systems
协作研究:SHF:中:以内存为中心的计算系统的硬件和软件支持
  • 批准号:
    2312509
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Continuing Grant
FAI: A novel paradigm for fairness-aware deep learning models on data streams
FAI:数据流上具有公平意识的深度学习模型的新颖范式
  • 批准号:
    2147375
  • 财政年份:
    2022
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
Collaborative Research: SHF: Medium: A New Direction of Research and Development to Fulfill the Promise of Computational Storage
合作研究:SHF:Medium:实现计算存储承诺的研发新方向
  • 批准号:
    2210755
  • 财政年份:
    2022
  • 资助金额:
    $ 50万
  • 项目类别:
    Continuing Grant
III: Small: Collaborative Research: A novel paradigm for detecting complex anomalous patterns in multi-modal, heterogeneous, and high-dimensional multi-source data sets
III:小型:协作研究:一种检测多模态、异构和高维多源数据集中复杂异常模式的新范式
  • 批准号:
    1954409
  • 财政年份:
    2019
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
CAREER: SPARK: A Theoretical Framework for Discovering Complex Patterns in Big Attributed Networks
职业:SPARK:发现大属性网络中复杂模式的理论框架
  • 批准号:
    1954376
  • 财政年份:
    2019
  • 资助金额:
    $ 50万
  • 项目类别:
    Continuing Grant
SHF: Small: Redesigning the System Architecture for Ultra-High Density Data Storage
SHF:小型:重新设计超高密度数据存储的系统架构
  • 批准号:
    1910958
  • 财政年份:
    2019
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
CAREER: SPARK: A Theoretical Framework for Discovering Complex Patterns in Big Attributed Networks
职业:SPARK:发现大属性网络中复杂模式的理论框架
  • 批准号:
    1750911
  • 财政年份:
    2018
  • 资助金额:
    $ 50万
  • 项目类别:
    Continuing Grant
III: Small: Collaborative Research: A novel paradigm for detecting complex anomalous patterns in multi-modal, heterogeneous, and high-dimensional multi-source data sets
III:小型:协作研究:一种检测多模态、异构和高维多源数据集中复杂异常模式的新范式
  • 批准号:
    1815696
  • 财政年份:
    2018
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
XPS: FULL: Collaborative Research: Maximizing the Performance Potential and Reliability of Flash-based Solid State Devices for Future Storage Systems
XPS:完整:协作研究:最大限度地提高未来存储系统基于闪存的固态设备的性能潜力和可靠性
  • 批准号:
    1629291
  • 财政年份:
    2016
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant

相似国自然基金

复合低维拓扑材料中等离激元增强光学响应的研究
  • 批准号:
    12374288
  • 批准年份:
    2023
  • 资助金额:
    52 万元
  • 项目类别:
    面上项目
基于管理市场和干预分工视角的消失中等企业:特征事实、内在机制和优化路径
  • 批准号:
    72374217
  • 批准年份:
    2023
  • 资助金额:
    41.00 万元
  • 项目类别:
    面上项目
托卡马克偏滤器中等离子体的多尺度算法与数值模拟研究
  • 批准号:
    12371432
  • 批准年份:
    2023
  • 资助金额:
    43.5 万元
  • 项目类别:
    面上项目
中等质量黑洞附近的暗物质分布及其IMRI系统引力波回波探测
  • 批准号:
    12365008
  • 批准年份:
    2023
  • 资助金额:
    32 万元
  • 项目类别:
    地区科学基金项目
中等垂直风切变下非对称型热带气旋快速增强的物理机制研究
  • 批准号:
    42305004
  • 批准年份:
    2023
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目

相似海外基金

III : Medium: Collaborative Research: From Open Data to Open Data Curation
III:媒介:协作研究:从开放数据到开放数据管理
  • 批准号:
    2420691
  • 财政年份:
    2024
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
Collaborative Research: III: Medium: Designing AI Systems with Steerable Long-Term Dynamics
合作研究:III:中:设计具有可操纵长期动态的人工智能系统
  • 批准号:
    2312865
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
Collaborative Research: III: MEDIUM: Responsible Design and Validation of Algorithmic Rankers
合作研究:III:媒介:算法排序器的负责任设计和验证
  • 批准号:
    2312932
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
III: Medium: Collaborative Research: Integrating Large-Scale Machine Learning and Edge Computing for Collaborative Autonomous Vehicles
III:媒介:协作研究:集成大规模机器学习和边缘计算以实现协作自动驾驶汽车
  • 批准号:
    2348169
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Continuing Grant
Collaborative Research: III: Medium: Algorithms for scalable inference and phylodynamic analysis of tumor haplotypes using low-coverage single cell sequencing data
合作研究:III:中:使用低覆盖率单细胞测序数据对肿瘤单倍型进行可扩展推理和系统动力学分析的算法
  • 批准号:
    2415562
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了