University of Oregon Planning Proposal: I/UCRC for Big Learning

俄勒冈大学规划提案：I/UCRC for Big Learning

• 批准号: 1650587
• 负责人: Dejing Dou
• 金额: $ 1.5万
• 依托单位: University of Oregon Eugene
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-02-15 至 2018-01-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1650587&HistoricalAwards=false
• 关键词: University; Oregon; Planning; Proposal; UCRC

The proposed NSF I/UCRC Center for Big Learning (CBL) consists of multi-disciplinary experts at the four founding universities that are geographically distributed across the country: University of Oregon (UO, West), Carnegie Mellon University (CMU, East), University of Missouri at Kansas City (UMKC, Central), and University of Florida (UF, South). The mission of this center is to explore research frontiers in the design of novel algorithms and developing efficient systems for deep learning research and its applications in the era of big data and big systems. Through a multi-site and multi-disciplinary consortium, the CBL center at the UO will focus on key applications of large-scale deep learning involving multi-modal media (i.e., text, image, and Q&A) in various domains (i.e., health, life science, IoT/mobile, and business) relying on strong support from the industry partners. The proposed multidisciplinary center will offer important opportunities for training new scientists and graduate students, and provide an environment for cross-disciplinary engagement.The research team at the UO includes experts in data science, artificial intelligence, machine learning, high performance computing, IoT, health informatics, and bioinformatics. The CBL at the UO seeks to catalyze the fusion of expertise from academia, government, and industry stakeholders related to the rapid innovation in algorithms, systems, applications as well as education, and technology transfer into cutting-edge products and services with real-world relevance and significance. The UO site will explore several research projects related to health behavior modeling, activity recommendation, social network analysis, and privacy preserving by deploying various deep learning models. The planning activities will lead to a successful proposal for the establishment of the CBL center with a solid consortium across multiple campuses and a large number of industry partners. Our proposed meetings, forums, conferences, and planned training sessions will greatly promote and broaden the research and materialization of large-scale deep learning.

拟议的 NSF I/UCRC 大学习中心 (CBL) 由分布在全国各地的四所创始大学的多学科专家组成：俄勒冈大学（UO，西）、卡内基梅隆大学（CMU，东）、密苏里大学堪萨斯城分校（UMKC，中部）和佛罗里达大学（佛罗里达大学，南部）。 该中心的使命是探索设计新颖算法和开发高效系统的研究前沿，以进行深度学习研究及其在大数据和大系统时代的应用。通过多地点、多学科联盟，俄勒冈大学的 CBL 中心将重点关注涉及多模态媒体（即文本、图像和问答）的大规模深度学习在各个领域（即健康领域）的关键应用。 、生命科学、物联网/移动和商业）依赖于行业合作伙伴的大力支持。拟建的多学科中心将为培养新科学家和研究生提供重要机会，并提供跨学科参与的环境。俄勒冈大学的研究团队包括数据科学、人工智能、机器学习、高性能计算、物联网、健康信息学和生物信息学。俄勒冈大学的 CBL 致力于促进学术界、政府和行业利益相关者的专业知识的融合，这些专业知识涉及算法、系统、应用程序以及教育的快速创新，以及将技术转化为现实世界的尖端产品和服务。相关性和意义。俄勒冈大学网站将通过部署各种深度学习模型来探索与健康行为建模、活动推荐、社交网络分析和隐私保护相关的多个研究项目。规划活动将促成建立 CBL 中心的成功提案，该中心拥有跨多个校区的坚实联盟和大量行业合作伙伴。我们提议的会议、论坛、大会和计划的培训课程将极大地促进和拓宽大规模深度学习的研究和具体化。

项目成果

A Temporal Attentional Model for Rumor Stance Classification

谣言立场分类的时间注意模型

• DOI: 10.1145/3132847.3133116
• 发表时间: 2017-11-06
• 期刊: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management
• 作者: Amir Pouran Ben Veyseh;J. Ebrahimi;D. Dou;Daniel Lowd
• 通讯作者: Daniel Lowd

Time-Sensitive Behavior Prediction in a Health Social Network

健康社交网络中的时间敏感行为预测

• DOI: 10.1109/icmla.2017.000-4
• 发表时间: 2017-12
• 期刊: Proceedings of 16th IEEE International Conference on Machine Learning and Applications (ICMLA
• 作者: Amimeur, Amnay;Phan, NhatHai;Dou, Dejing;Kil, David;Piniewski, Brigitte
• 通讯作者: Piniewski, Brigitte

Ontology-based deep learning for human behavior prediction with explanations in health social networks

基于本体的深度学习用于人类行为预测以及健康社交网络中的解释

• DOI: 10.1016/j.ins.2016.08.038
• 发表时间: 2017-04
• 期刊: Information sciences
• 影响因子: 8.1
• 作者: Phan N;Dou D;Wang H;Kil D;Piniewski B
• 通讯作者: Piniewski B