时间: 14:00-15:30 on Fri.,Jul.7, 2023

地点：生物医学馆E203会议室

主讲人: Dr.Guoqiang Yu

主持人:Dr.Songhai Shi（时松海）

题目: Machine Learning Techniques to Assist and Empower Biomedical Research

摘要：

Machine learning and artificial intelligence have significantly changed the industry and impacted many aspects of our life. In this talk, we will present some of our research work, illustrating how the machine learning techniques can assistant and empower scientific research, especially, the biomedical research, and reciprocally how cutting-edge scientific research problems can motivate the development of advanced machine learning techniques. Particularly, we will discuss (1) how a new analysis framework was developed to quantify the fluorescent complex cellular and subcellular brain activity, (2) how computational approaches can enable the large-scale lineage analysis of embryo development and microglia mobility analysis, (3) how machine learning models can explore and utilize the super-large volumetric EM data, (4) how sophisticated statistical modeling and advanced optimization techniques can unify and improve various genomic analysis tasks, such as driving transcription factor identification, single-cell sequencing analysis, cancer-associated gene detection, and single-cell-level similarity quantification.

报告人简介：

Dr. Guoqiang Yu is currently a Professor at the Bradley Department of Electrical and Computer Engineering, Virginia Tech. He received his B.S. degree in electrical and computer engineering from Shandong University in 2001 and M.S. degree in automation from Tsinghua University in 2004. He received his Ph.D. degree in electrical and computer engineering from Virginia Tech in 2011. He did his Postdoctoral training in Bioinformatics at Stanford University. His research interests are machine learning, signal and image analysis, statistical modeling, optimization techniques and their applications to developing computational tools to analyze and understand the big data in the biomedical field, particularly related to brain research. He has published 48 journal papers and 37 peer-reviewed conference papers, in journals such as Nature Neuroscience, Nature Medicine, Neuron, Bioinformatics, Science Advances, IEEE PAMI, and Journal of Machine Learning Research, and conferences such as NeurIPS and ICML. His most significant work includes the paradigm-shifting analysis framework AQuA on astrocyte activity quantification and the data-association algorithm CINDA setting the historical record on computational complexity. His work has been supported by NSF and NIH with a personal share of over 12 million US dollars. He is a recipient of NSF CAREER award, Dean's Award for Excellence in Research, and COE Faculty Fellow Award. He currently serves as an associate editor for the journals Bioinformatics Advances, and BMC Bioinformatics. He has received four best paper awards including Neuron (2019), the IEEE International Conference on Bioinformatics and Biomedicine (2009 and 2016) and the William A. Blackwell Award of Virginia Tech (2009).