Foundations for Robust and Minimally-Supervised Learning Systems
稳健和最低限度监督学习系统的基础
基本信息
- 批准号:RGPIN-2022-03215
- 负责人:
- 金额:$ 2.11万
- 依托单位:
- 依托单位国家:加拿大
- 项目类别:Discovery Grants Program - Individual
- 财政年份:2022
- 资助国家:加拿大
- 起止时间:2022-01-01 至 2023-12-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Background. Machine learning, a technology that develops software through learning from historical experience and inferencing the properties of new data by its generalization ability, has been largely driven by the availability of big data. However, labeling of big data by human annotators is costly, and machine learning generalization ability is often susceptible to adversarial attacks and out-of-distribution data. For example, a tiny adversarial patch attached to a stop sign could completely fool autopilot systems, even though the systems were trained with as many as 3-billion-mile real data collected over 6 years, quoted from Tesla's 2020 report. Objectives. The long-term goal of the proposed research program is to advance machine learning from the robustness and self-supervision perspectives, by developing generic, principled, and scalable algorithms with provable guarantees and practical applications. Therefore, the objectives include: 1) developing new robust models against unrestricted adversarial examples and out-of-distribution data and connecting robustness with fairness, privacy and interpretability towards trustworthy machine learning; 2) closing the performance gap between supervised and self-supervised learning; and 3) applying the proposed robust and self-supervised framework to the real-world tasks, including 3D reconstruction, textual analysis, and Deepfake detection. Impacts and Reward. The developed robust method is expected to serve as the first baseline to encourage the development of new defenses against a broader class of adversarial attacks. The technology will potentially accelerate the research and development of autonomous cars, making AI safe, reliable, transparent, and trustworthy in Canada. Moreover, this research will significantly reduce the cost of data labeling for high-tech companies in Canada. The proposed research program will improve the state-of-the-art of real-time 3D perception for robotics navigation, AR/VR for Metaverse, textual analysis in the presence of typos, and fake video detection on YouTube and Twitter. Students will learn the necessary skills to carry out a research plan, scientific writing, critical thinking, and coding. By the end of their program, the students will become machine learning experts who are well-positioned for industrial research scientist positions or academic research positions in top universities.
背景机器学习是一种通过从历史经验中学习并通过其泛化能力推断新数据属性来开发软件的技术,它在很大程度上受到大数据可用性的推动。然而,人类注释者对大数据进行标记的成本很高,而且机器学习的泛化能力往往容易受到对抗性攻击和分布外数据的影响。例如,特斯拉2020年的报告中提到,附着在停车标志上的一个微小的对抗性补丁可以完全欺骗自动驾驶系统,尽管这些系统是用6年来收集的多达30亿英里的真实的数据训练的。目标.拟议研究计划的长期目标是通过开发具有可证明保证和实际应用的通用、原则性和可扩展算法,从鲁棒性和自我监督的角度推进机器学习。因此,目标包括:1)针对不受限制的对抗性示例和分布外数据开发新的鲁棒模型,并将鲁棒性与公平性,隐私性和可解释性联系起来,以实现可信的机器学习; 2)缩小监督学习和自监督学习之间的性能差距;以及3)将所提出的鲁棒和自监督框架应用于现实世界的任务,包括3D重建,文本分析和Deepfake检测。影响和奖励。开发的强大方法预计将作为第一个基线,以鼓励开发针对更广泛类别的对抗性攻击的新防御。该技术将有可能加速自动驾驶汽车的研发,使人工智能在加拿大安全、可靠、透明和值得信赖。此外,这项研究将大大降低加拿大高科技公司的数据标签成本。拟议的研究计划将改善机器人导航的实时3D感知,Metaverse的AR/VR,存在错别字的文本分析以及YouTube和Twitter上的虚假视频检测的最新技术。学生将学习必要的技能,进行研究计划,科学写作,批判性思维和编码。在课程结束时,学生将成为机器学习专家,他们将在顶尖大学的工业研究科学家职位或学术研究职位上处于有利地位。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
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 }}
Zhang, Hongyang其他文献
Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games
对抗鲁棒性博弈中的纳什均衡和对抗训练的陷阱
- DOI:
- 发表时间:
2023 - 期刊:
- 影响因子:0
- 作者:
Balcan, Maria-Florina;Pukdee, Rattana;Ravikumar, Pradeep;Zhang, Hongyang - 通讯作者:
Zhang, Hongyang
Drusen Volume as a Predictor of Disease Progression in Patients With Late Age-Related Macular Degeneration in the Fellow Eye
- DOI:
10.1167/iovs.15-18572 - 发表时间:
2016-04-01 - 期刊:
- 影响因子:4.4
- 作者:
Abdelfattah, Nizar Saleh;Zhang, Hongyang;Sadda, SriniVas R. - 通讯作者:
Sadda, SriniVas R.
Influence of Phenylmethylsilicone Oil on Anti-Fouling and Drag-Reduction Performance of Silicone Composite Coatings
苯甲基硅油对有机硅复合涂层防污减阻性能的影响
- DOI:
10.3390/coatings10121239 - 发表时间:
2020-12-01 - 期刊:
- 影响因子:3.4
- 作者:
Yang, Qiang;Zhang, Zhanping;Zhang, Hongyang - 通讯作者:
Zhang, Hongyang
Identification of flavonol and triterpene glycosides in Luo-Han-Guo extract using ultra-high performance liquid chromatography/quadrupole time-of-flight mass spectrometry
超高效液相色谱/四极杆飞行时间质谱法鉴定罗汉果提取物中的黄酮醇和三萜苷
- DOI:
10.1016/j.jfca.2011.09.004 - 发表时间:
2012-03-01 - 期刊:
- 影响因子:4.3
- 作者:
Zhang, Hongyang;Yang, Huihua;Hu, Ping - 通讯作者:
Hu, Ping
A novel optimal management method for smart grids incorporating cloud-fog layer and honeybee mating optimization algorithm
- DOI:
10.1016/j.solener.2023.111874 - 发表时间:
2023-07-23 - 期刊:
- 影响因子:6.7
- 作者:
Zhang, Hongyang;Sun, Rui - 通讯作者:
Sun, Rui
Zhang, Hongyang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('Zhang, Hongyang', 18)}}的其他基金
Foundations for Robust and Minimally-Supervised Learning Systems
稳健和最低限度监督学习系统的基础
- 批准号:
DGECR-2022-00357 - 财政年份:2022
- 资助金额:
$ 2.11万 - 项目类别:
Discovery Launch Supplement
相似国自然基金
供应链管理中的稳健型(Robust)策略分析和稳健型优化(Robust Optimization )方法研究
- 批准号:70601028
- 批准年份:2006
- 资助金额:7.0 万元
- 项目类别:青年科学基金项目
心理紧张和应力影响下Robust语音识别方法研究
- 批准号:60085001
- 批准年份:2000
- 资助金额:14.0 万元
- 项目类别:专项基金项目
ROBUST语音识别方法的研究
- 批准号:69075008
- 批准年份:1990
- 资助金额:3.5 万元
- 项目类别:面上项目
改进型ROBUST序贯检测技术
- 批准号:68671030
- 批准年份:1986
- 资助金额:2.0 万元
- 项目类别:面上项目
相似海外基金
VIPAuto: Robust and Adaptive Visual Perception for Automated Vehicles in Complex Dynamic Scenes
VIPAuto:复杂动态场景中自动驾驶车辆的鲁棒自适应视觉感知
- 批准号:
EP/Y015878/1 - 财政年份:2024
- 资助金额:
$ 2.11万 - 项目类别:
Fellowship
CAREER: Game Theoretic Models for Robust Cyber-Physical Interactions: Inference and Design under Uncertainty
职业:稳健的网络物理交互的博弈论模型:不确定性下的推理和设计
- 批准号:
2336840 - 财政年份:2024
- 资助金额:
$ 2.11万 - 项目类别:
Continuing Grant
CAREER: Structured Minimax Optimization: Theory, Algorithms, and Applications in Robust Learning
职业:结构化极小极大优化:稳健学习中的理论、算法和应用
- 批准号:
2338846 - 财政年份:2024
- 资助金额:
$ 2.11万 - 项目类别:
Continuing Grant
Robust Transient State Estimation for Three-Phase Power Systems
三相电力系统的鲁棒瞬态估计
- 批准号:
2330377 - 财政年份:2024
- 资助金额:
$ 2.11万 - 项目类别:
Standard Grant
NSF Convergence Accelerator track L: Translating insect olfaction principles into practical and robust chemical sensing platforms
NSF 融合加速器轨道 L:将昆虫嗅觉原理转化为实用且强大的化学传感平台
- 批准号:
2344284 - 财政年份:2024
- 资助金额:
$ 2.11万 - 项目类别:
Standard Grant
Research on Robust Multi-Person Gait Recognition Based on the Combination of Human Mesh Model and Silhouette
基于人体网格模型与剪影相结合的鲁棒多人步态识别研究
- 批准号:
24K20794 - 财政年份:2024
- 资助金额:
$ 2.11万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
CAREER: Robust, Fair, and Culturally Aware Commonsense Reasoning in Natural Language
职业:用自然语言进行稳健、公平和具有文化意识的常识推理
- 批准号:
2339746 - 财政年份:2024
- 资助金额:
$ 2.11万 - 项目类别:
Continuing Grant
CAREER: Optimal Transport Beyond Probability Measures for Robust Geometric Representation Learning
职业生涯:超越概率测量的最佳传输以实现稳健的几何表示学习
- 批准号:
2339898 - 财政年份:2024
- 资助金额:
$ 2.11万 - 项目类别:
Continuing Grant
Collaborative Research: Robust and miniature laser with tailorable single-mode operation range
合作研究:具有可定制单模工作范围的坚固微型激光器
- 批准号:
2411394 - 财政年份:2024
- 资助金额:
$ 2.11万 - 项目类别:
Standard Grant
CAREER: Robust Reinforcement Learning Under Model Uncertainty: Algorithms and Fundamental Limits
职业:模型不确定性下的鲁棒强化学习:算法和基本限制
- 批准号:
2337375 - 财政年份:2024
- 资助金额:
$ 2.11万 - 项目类别:
Continuing Grant