Colloquium
- Fausto Milletari, Lead of Applied AI, Johnson and JohnsonVolumetric medical image processing with deep learning One of the fundamental capabilities of deep learning is its ability of accomplishing a multitude of tasks by learning features
- Andrey Zhmoginov, Research Software Engineer, Google AIImage understanding and image-to-image translation through the lens of information loss The computation performed by a deep neural network is typically composed of multiple processing stages
- Muyinatu A. Lediju Bell, Assistant Professor of Electrical and Computer Engineering, Biomedical Engineering, and Computer Science, Johns Hopkins UniversityUltrasound Image Formation in the Deep Learning AgeThe success of diagnostic and
- Sanja Fidler, Department of Computer Science, University of Toronto; and Director of AI, NVIDIA corporationTowards AI for 3D Content Creation3D content is key in several domains such as architecture, film, gaming, and robotics. However, creating 3D
- Ruslan Salakhutdinov, UPMC Professor of Computer Science, Department of Machine Learning, Carnegie Mellon UniversityIntegrating Domain-Knowledge into Deep Learning.In this talk I will first discuss deep learning models that can find semantically
- Colin Raffel; Assistant Professor of Computer Science; University of North Carolina, Chapel Hill; and Staff Research Scientist, Google BrainT5 and large language models: The good, the bad, and the uglyT5 and other large pre-trained language
- Stephen Kissler, Postdoctoral Fellow at Harvard T.H. Chan School of Public HealthSARS-CoV-2 across scalesMathematical models have provided key insights into SARS-CoV-2 dynamics at the global, local, and physiological scales. I will summarize some of
- Marsha Berger; Silver Professor of Computer Science and Mathematics; Courant Institute of Mathematical Sciences, New York UniversityComputing Fluid Flows in Complex GeometryWe give an overview of the difficulties in simulating fluid flow in complex
- Adrianna Gillman, Department of Applied Mathematics, University of Colorado BoulderFast algorithms group: Accurate, efficient and robust techniques for solving partial differential equationsPartial differential equations are often used to model
- APPM Department Colloquium - Joan BrunaJoan Bruna; Assistant Professor; Courant Institute of Mathematical Sciences, New York UniversityMathematical aspects of neural network approximation and learningHigh-dimensional learning remains an