Two months ago, University of Waterloo’s Vision and Image Processing (VIP) Lab and DarwinAI released a preprint of their COVID-Net research on designing a convolutional neural network for detecting COVID-19 from X-rays. Last month, SigOpt launched SigOpt for Good, which extends free access to our product for any COVID-19 research. As part of this program, SigOpt collaborated with a member of the VIP lab to tune data augmentation parameters of COVID-Net to better understand how data augmentation plays a role in COVID-Net performance.
In this talk, lead researcher Alexander Wong from DarwinAI discusses with Michael McCourt from SigOpt his insights on the design, development, optimization, and impact of COVID-Net. Among other topics, this discussion will cover:
This talk is great for deep learning practitioners interested in a vision use case, researchers focused on health-related data, or anyone interested in learning about novel applications of deep learning to COVID-19 research.
For any researcher interested in using SigOpt for free on their COVID work, please reach out to us here: https://tuning.sigopt.com/sigopt-for-good
Mike studies mathematical and statistical tools for interpolation and prediction. Prior to joining SigOpt, he spent time in the math and computer science division at Argonne National Laboratory and was a visiting assistant professor at the University of Colorado-Denver where he co-wrote a text on kernel-based approximation. Mike holds a Ph.D. and MS in Applied Mathematics from Cornell and a BS in Applied Mathematics from Illinois Institute of Technology.
Dr. Wong, P.Eng., is currently the Canada Research Chair in Artificial Intelligence and Medical Imaging, a member of the College of the Royal Society of Canada, Co-director of the Vision and Image Processing Research Group, Found Member of the Waterloo Artificial Intelligence Institute, Associate Professor in the Department of Systems Design Engineering at the University of Waterloo, and Co-founder and Chief Scientist of DarwinAI. His research background includes artificial intelligence, computer vision, and computational imaging, and he has published over 500 refereed journal and conference papers, as well as filing several patents in these areas. In AI, he focuses on operational AI (co-inventor of Generative Synthesis, evolutionary deep intelligence, Deep Bayesian Residual Transform, Discovery Radiomics, and random deep intelligence via deep-structured fully-connected graphical models), and particularly on explainable deep learning and AI-assisted AI design. Dr. Wong has received various awards for his work, including a Best Paper Award at the NeurIPS Workshop on Transparent and Interpretable Machine Learning (2017), a Best Paper Award at the NeurIPS Workshop on Efficient Methods for Deep Neural Networks (2016), three Outstanding Performance Awards, a Distinguished Performance Award, an Engineering Research Excellence Award, a Sandford Fleming Teaching Excellence Award, an Early Researcher Award from the Ministry of Economic Development and Innovation, two Best Paper Awards by the Canadian Image Processing and Pattern Recognition Society (CIPPRS) (2009 and 2014), a Distinguished Paper Award by the Society of Information Display (2015), four Best Paper Awards for the Conference of Computer Vision and Imaging Systems (CVIS) (2015, 2017, 2018, 2019), and a Synaptive Best Medical Imaging Paper Award (2016).