Yonina Eldar
Joseph E. Aoun Professor, Northeastern University
Talk recording
Deep neural networks have achieved unprecedented performance gains across numerous real-world signal and image processing tasks. However, their widespread adoption and practical deployment are often limited by their black-box nature—characterized by a lack of interpretability and a reliance on large training datasets. In contrast, traditional approaches in signal processing, sensing, and communications have long leveraged classical statistical modeling techniques, which incorporate mathematical formulations based on underlying physical principles, prior knowledge, and domain expertise. While these models offer valuable insights, they can be overly simplistic and sensitive to inaccuracies, leading to suboptimal performance in complex or dynamic real-world scenarios. This talk explores various approaches to model-based learning which merge parametric models with optimization tools and classical algorithms to create efficient, interpretable deep networks that require significantly smaller training datasets. We demonstrate the advantages of this approach through applications in image deblurring, image separation, super-resolution for ultrasound and microscopy, radar for clinical diagnostics, efficient communication systems, low-power sensing devices, and more. Additionally, we present theoretical results that establish the performance advantages of model-based deep networks over purely data-driven black-box methods.
About the speaker
Yonina Eldar is the Aoun Chair Professor of Electrical and Computer Engineering at Northeastern University. She founded and heads the Signal Acquisition Modeling Processing and Learning Lab (SAMPL) and the Center for Biomedical Engineering at the Weizmann Institute. She is also a Visiting Professor at MIT and Princeton, a Visiting Scientist at the Broad Institute, and an Adjunct Professor at Duke University and was a Visiting Professor at Stanford. She is a member of the Israel Academy of Sciences and Humanities and of the Academia Europaea, an IEEE Fellow and a EURASIP Fellow. She received the B.Sc. degree in physics and the B.Sc. degree in electrical engineering from Tel-Aviv University, and the Ph.D. degree in electrical engineering and computer science from MIT. She has received many awards for excellence in research and teaching, including the Israel Prize (2025), Landau Prize (2024), IEEE Signal Processing Society Technical Achievement Award (2013), the IEEE/AESS Fred Nathanson Memorial Radar Award (2014) and the IEEE Kiyo Tomiyasu Award (2016). She received the Michael Bruno Memorial Award from the Rothschild Foundation, the Weizmann Prize for Exact Sciences, the Wolf Foundation Krill Prize for Excellence in Scientific Research, the Henry Taub Prize for Excellence in Research (twice), the Hershel Rich Innovation Award (three times), and the Award for Women with Distinguished Contributions. She was selected as one of the 50 most influential women in Israel, and was a member of the Israel Committee for Higher Education. She is the Editor in Chief of Foundations and Trends in Signal Processing, a member of several IEEE Technical Committees and Award Committees, and heads the Committee for Promoting Gender Fairness in Higher Education Institutions in Israel.
Share this page:
