James Zou, PhD
Assistant Professor of Biomedical Data Science and, by courtesy, of Computer Science and of Electrical Engineering
Stanford University
Title: Computer Vision to Phenotype Human Diseases Across Physiological and Molecular Scales.
Abstract: I will present new computer vision algorithms to learn complex morphologies and phenotypes that are important for human diseases. I will illustrate this approach with examples that capture physical scales from macro to micro: 1) video-based AI to assess heart function (Ouyang et al Nature 2020), 2) generating spatial transcriptomics from histology images (He et al Nature BME 2020), 3) and learning morphodynamics of immune cells. Throughout the talk I’ll illustrate new design principles/tools for human-compatible and robust AI that we developed to enable these technologies (Ghorbani et al. NeurIPS 2020, Abid et al. Nature MI 2020).
Bio: James Zou is an assistant professor of biomedical data science and, by courtesy, of CS and EE at Stanford University. He is also a Chan-Zuckerberg investigator. James develops novel machine learning algorithms that have strong statistical guarantees and that are motivated by human health challenges. Several of his methods are widely used by tech, biotech and pharma companies. He also works on questions important for the broader impacts of AI—fairness, accountability, interpretations, and robustness. He has received 5 best paper awards at top CS venues, a NSF CAREER Award, a Google Faculty Award, and a Tencent AI award.