Search results

Section: Publications & Resources

Publication: IEEE Signal Processing Magazine

Deep learning (DL) has been wildly successful in practice, and most of the state-of-the-art machine learning methods are based on neural networks (NNs). Lacking, however, is a rigorous mathematical theory that adequately explains the amazing performance of deep NNs (DNNs). In this article, we present a relatively new mathematical framework that provides the beginning of a deeper understanding of DL. This framework precisely characterizes the functional properties of NNs that are trained to fit to data. The key mathematical tools that support this framework include transform-domain sparse regularization, the Radon transform of computed tomography, and approximation theory, which are all techniques deeply rooted in signal processing.

Section: Publications & Resources

Publication: IEEE Signal Processing Magazine

Quaternions are still largely misunderstood and often considered an “exotic” signal representation without much practical utility despite the fact that they have been around the signal and image processing community for more than 30 years now. The main aim of this article is to counter this misconception and to demystify the use of quaternion algebra for solving problems in signal and image processing. To this end, we propose a comprehensive and objective overview of the key aspects of quaternion representations, models, and methods and illustrate our journey through the literature with flagship applications. We conclude this work by an outlook on the remaining challenges and open problems in quaternion signal and image processing.

Section: Publications & Resources

Publication: IEEE Signal Processing Magazine

Inference tasks in signal processing are often characterized by the availability of reliable statistical modeling with some missing instance-specific parameters. One conventional approach uses data to estimate these missing parameters and then infers based on the estimated model. Alternatively, data can also be leveraged to directly learn the inference mapping end to end. These approaches for combining partially known statistical models and data in inference are related to the notions of generative and discriminative models used in the machine learning literature [1] , [2] , typically considered in the context of classifiers.

Section: Events

Date: 12-14 June 2024 Location: Taichung, Taiwan

Section: Publications & Resources

ME-UYR is under way! We are currently looking for students and mentors who are interested in participating in this mentoring experience. Please find more information in the Call for Student participants and the Call for Mentors.

Section: Events

Lecture Date: 17 October 2023 Chapter: Spain Chapter Chapter Chair: Javier Prieto Topic: Nonconvex Optimization Meets Low-Rank Matrix Estimation

Section: Events

Lecture Date: 19 October 2023 Chapter: France Chapter Chapter Chair: William Puech Topic: Reinforcement Learning meets Federated Learning and Distributional Robustness

Section: Events

Date: 21 November 2023 Chapter: German Chapter Chapter Chair: Wolfgang Utschick Topic: Differentiable Tools for Digital Twin Networks

Section: Events

Date:  18 October 2023 Chapter: North Jersey Chapter Chapter Chair: Alfredo Tan Title: Synthetic Aperture Radar (SAR) Signal Processing Challenges and Data Sets for Associated Research