Prof. Li Li, IEEE Fellow, CAA Fellow
Tsinghua University, China
Prof. Li Li is a Professor at Tsinghua University. He has been engaged in scientific research in the fields of artificial intelligence and intelligent systems. He has published more than 120 SCI search papers as the first or corresponding author. He was a member of the Editorial Advisory Board for Transportation Research Part C: Emerging Technologies, a member of the Editorial Board of Transport Reviews and ACTA Automatica Sinica. He serves as Associate Editors for the IEEE Transactions on Intelligent Transportation Systems and IEEE Transactions on Intelligent Vehicles. He is a Fellow of IEEE and a Fellow of CAA.
Speech Title: "Accelerating DNN Training Using Typicality Sampling and Achieving Better Generalization via Non-Typicality Sampling"
Abstract: Minibatch stochastic gradient descent (SGD) is one of the most popular stochastic optimization methods for training deep networks. However, it shows a slow convergence rate due to the large noise in the gradient approximation and may not always achieve good generalization capability. In this speech, we proposed a two-step sampling strategy for SGD. In the first step, we pay more attention to the samples that can generate more accurate search direction by providing the most informative gradient features. This will accelerate the training process. In the second step, we pay more attention to the rest samples to boost the generalization performance of DNNs through biasing the solution toward wider minima, under certain assumptions. Theoretical analysis and numerical testing results indicate the effectiveness of such new sampling strategy.
Prof. Jimmy Liu, IEEE Senior Member
Southern University of Science and Technology, China
Jimmy Liu graduated from the Department of Computer Science of the University of Science and Technology of China in 1988. He further obtained his master and doctoral degrees in Computer Science from the National University of Singapore. In 2004, he started and grew the Intelligent Medical Imaging Research Team (iMED Singapore), focusing on ocular Artificial Intelligence research. Jimmy was the chairman of the IEEE Singapore Biomedical Engineering Society in Singapore before moving to China. In March 2016, Jimmy moved to China and became the founding institute director of the Cixi Institute of Biomedical Engineering (CIBE) under the Chinese Academy of Sciences (CAS). He further founded the iMED China Ningbo team in CIBE focusing on ocular image AI research. In February 2019, he joined the Department of Computer Science and Engineering of the Southern University of Science and Technology and established iMED China Shenzhen continue to focus on ocular AI image AI research. Right now, iMED China team are devoting themselves to eye-brain imaging, ocular imaging, ocular precision medicine, and ocular surgical robotics 4 research areas.
Speech Title: "Intelligent Ocular Image Process – Research Update of iMED Team"
Abstract: Jimmy will talk about the modalities, methods, algorithms of the ocular imaging research. He will also highlight the iMED team (www.imed-lab.com) latest research progress in the past one year in ocular image enhancement, retinal blood vessel reconstruction, AS-OCT glaucoma screening, search-based ocular disease diagnosis, corneal endothelial cell detection, etc.
Prof. Ruikang Wang, OSA Fellow, SPIE Fellow and AIMBE Fellow
University of Washington, USA
Dr. Wang is a professor of bioengineering and ophthalmology at the University of Washington. He also holds the prestigious positions of George and Martina Kren Endowed Chair In Ophthalmology Research and WRF/David and Nancy Auth Endowed Innovator of Bioengineering. His current research interests include biophotonics and imaging, optical coherence tomography and their applications in ophthalmology, neuroscience, dermatology and cancer. Dr Wang has published over 500 peer reviewed journal articles. He is an elected fellow of Optica, SPIE and AIMBE. He is also the Editor in Chief for Biomedical Optics Express, an Optica Publishing Group journal.
Speech Title: "Advances in Optical Coherence Tomography Angiography"
Abstract: Optical coherence tomography angiography (OCTA) is a new medical imaging modality in which OCT is used to create functional retinal microvascular networks with high resolution without a need for contrasting dyes. Our group is responsible for the development of optical microangiography (OMAG) that was subsequently ported to Carl Zeiss OCT systems, including spectral domain and swept source OCT configurations. The ability to visualize functional microvascular blood flow is important in a variety of diseases, some of which (along with the OCTA/OMAG basics and the enabling technologies) will be highlighted in this talk. Clinical examples using OCTA will be given, including ophthalmology, dermatology and dentistry.