October 28, 2020
Compressive Sensing Meets Machine Learning
Ali Gurbuz | email@example.com
Abstract: In this talk, I will introduce several machine learning based projects going on in IMPRESS Lab and present several recent results on compressive learning. Since the revolution of digital age, sensors acquire data in a fixed way independent of the task and how that data can be utilized. Compressive sensing (CS) revised data acquisition by utilizing sparse data models and provided a novel data acquisition and processing method which allows reconstruction of sparse signals with much lower number of measurements than what is implied by the Nyquist rate. CS has created many applications from medical imaging, to radar or wireless communications. However, the data acquisition is still not task driven or adaptive. This talk will introduce learning-based frameworks mimicking compressive sensing structures for modeling and integrating data acquisition and signal processing tasks, such as reconstruction or inference, with learnable network structures. Recent results on machine learning based signal reconstruction and learning optimal set of measurements for a given signal class will be provided. Join me to see how the two main topics in the last decade of signal processing research, compressive sensing and machine learning, come together in a joint framework.
Biographical info: Dr. Ali Cafer Gurbuz received B.S. degree from Bilkent University, Ankara, Turkey, in 2003, in Electrical Engineering, and the M.S. and Ph.D. degrees from Georgia Institute of Technology, Atlanta, GA, USA, in 2005 and 2008, both in Electrical and Computer Engineering. From 2003 to 2009, he researched compressive sensing based computational imaging problems at Georgia Tech as both research assistant and post-doctoral fellow. He held
faculty positions at both assistant and associate professor levels at TOBB University, Turkey, between 2009 and 2016, where he pursued an active research program on the development of sparse signal representations, compressive sensing theory and applications, radar and sensor array signal processing, and machine learning. Currently, he is an Assistant Professor at Mississippi State University, Department of Electrical and Computer Engineering, where he is co-director of Information Processing and Sensing (IMPRESS) Lab. He is the recipient of The Best Paper Award for Signal Processing Journal in 2013 and the Turkish Academy of Sciences Best Young Scholar Award in Electrical Engineering in 2014. He has served as an associate editor for several journals such as Digital Signal Processing, EURASIP Journal on Advances in Signal Processing and Physical Communications. He is a senior member of IEEE.
* For further information contact: Dr. Jenny Du | firstname.lastname@example.org | 5-2035
For WebEx Information, scan the QR