Qi Yu - Featured Faculty 2018
Qi Yu
Golisano College of Computing and Information Sciences
QI YU’S RESEARCH SPANS MULTIPLE BRANCHES IN MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE WITH A MAJOR FOCUS ON INTEGRATING MACHINE INTELLIGENCE WITH HUMAN INTELLIGENCE THROUGH INNOVATIONS IN MULTIMODAL DATA FUSION, DYNAMIC DATA MODELING, ACTIVE LEARNING, BAYESIAN NONPARAMETRICS, AND KNOWLEDGE-RICH DATA MINING. DR. YU HAS RECEIVED OVER $2M IN RESEARCH FUNDING, INCLUDING THOSE FROM THE NATIONAL SCIENCE FOUNDATION (NSF) AND THE OFFICE OF NAVAL RESEARCH (ONR).
Dr. Yu directs the Machine learning and Data Intensive Computing (Mining) research lab, which focuses on developing interpretable machine learning models that analyze large-scale multimodal dynamic data while keeping humans in the loop for interactive and continuous model improvement.
In a recently funded NSF project, Dr. Yu is working with an interdisciplinary research team to bring together human and computer capabilities to automatically extract the meaning of complex images, especially those from specialized domains such as medicine. The research will contribute novel computational models to capture the complex and unique features of human language and vision related to performing image understanding tasks, and an innovative probabilistic framework to fuse human knowledge data with image features.
In another project, which is sponsored by the ONR, Dr. Yu’s team aims to a develop a novel machine learning framework to facilitate complex decision-making in various highly complicated battlefield scenarios and military tasks. Such a framework will provide fundamental support to a decision-making team, including (1) analyzing large-scale, heterogeneous, and dynamic data streams from multiple sources and extracting high-level and meaningful features, (2) fusing multimodal data streams and providing decision recommendations with interpretable justifications, (3) identifying sources of uncertainty and offering informative guidance for cost-effective information gathering, and (4) allowing intuitive interactions with the human team for collaborative learning and continuous model improvement to achieve high-quality decisions.
Qi Yu
Associate Professor
Golisano College of Computing and Information Sciences