News
November 27, 2018
I have been selected (again) as a Clarivate Analytics Highly Cited Researcher
I have been selected (again) as a 2018 Clarivate Analytics (formerly Thompson-Reuters) Highly Cited Researcher. This list contains about 6000 scientists in various disciplines which represent the top 1% in their respective fields. Interestingly, only 18 of this list are from Israel, and I am the only Israeli representing the sub-field "Engineering". More on this list can be found here.October 5, 2018
Co-charing SIAM Imaging Sciences 2020 in Toronto
The SIAM-Imaging Sciences event, IS20, is scheduled to be held in Toronto in conjunction with the SIAM annual meeting during the week of July 6-10, 2020. Together with Stacey Levine, I will be chairing this meeting.June 5, 2018
2018 JVCI Best Paper Award
Our paper on Poisson inverse problems (with Arik Rond and Raja Giryes) has been announced as the winner of the 2018 JVCI Best Paper Award Honorable Mention.March 29, 2018
I have been selected as a Fellow of the Society for Industrial and Applied Mathematics (SIAM Fellow)
This fellowship honors SIAM members who have made outstanding contributions to the fields served by this organization. I am among a distinguished group of members nominated by our peers and selected for the 2018 Class of FellowsOctober 1, 2017
I am happy to bring to your attention a new Massive Open Online Course (MOOC)
I am happy to bring to your attention a new Massive Open Online Course (MOOC) that Yaniv Romano (my PhD student) and I have constructed on Sparse Representations. Here is the link under the edX webpage. This course will open formally on October 25th this year. It is built of two 5 weeks parts, the first presents the basic theoretical ideas of sparse representations, and the other connects this model to applications in image processing. In this course we are essentially following the content of my book. We will be delighted to see you joining our course, which could provide you with a pleasant introduction to our field.July 8, 2017
My paper with Michal Aharon on image denoising stands at the top of the list in the Signal Processing category
Google-Scholar released a list of what they refer to as the classic papers published during 2006. My paper with Michal Aharon on image denoising stands at the top of the list in theВ Signal Processing category. Also, my paper with David Donoho and Volodya Temlyakov on sparse representations is included in the classics of theВ Information Theory category.May 6, 2017
SIAM News has posted my article "Deep, Deep Trouble"
SIAM News has posted my article,В Deep, Deep Trouble, in its May 2017 issue. This article discusses the emerging field of deep learning and its impact on the research work in the image processing arena.December 18, 2016
I have been selected (again) as a Thomson-Reuters Highly Cited Researcher
I have been selected (again) as a Thomson-Reuters Highly Cited Researcher. This list contains about 3000 scientists in various disciplines. Interestingly, only 9 of this list are from Israel, and I am the only Israeli representing the subfield "Engineering". More on this list can be foundВ here.October 19, 2016
Deep-LearningВ offering a highly effective paradigm for supervised classification and regression
Deep-LearningВ is an emerging sub-field of machine-learning, offering a highly effective paradigm for supervised classification and regression. While empirical evidence puts this tool in the very forefront of today's artificial intelligence, both in the academia and the industry, theoretical understanding of this field has been lagging behind. I am proud to announce that ourВ recent workВ (joint with Vardan Papyan and Yaniv Romano) closes much of this gap. We propose an extension of the classic theory of sparse representations, modeling signals as hierarchical sparse compositions. For these signals we are able to show that fully-connected or convolutional neural networks (NN) are in fact pursuit algorithms, aiming to decompose the signals into their building atoms. With this view, we are able to analyze the performance of NN and consider various architectural improvements.September 19, 2015