Welcome to Prof. Michael Elad's personal page!Michael Elad is a Professor in the Computer Science Department of the Technion - Israel Institute of Technology. His fields of interest include signal processing, image processing, and computer vision; numerical analysis, numerical linear algebra and Machine learning algorithms. Follow the links at the top of the page to learn more...
Fax: (+972) 4-829-4353 or 3900
Office: Taub building 712, Technion
Computer Science Department
32000 Haifa, Israel
October 1, 2017 - 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 - 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 the Signal Processing category. Also, my paper with David Donoho and Volodya Temlyakov on sparse representations is included in the classics of the Information Theory category.
May 6, 2017 - SIAM News has posted my article, 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. 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 found here.
October 19, 2016 - Deep-Learning 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 our recent work (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 - I have been appointed Editor-in-Chief (EiC) of SIAM Journal on Imaging Sciences effective January 1st, 2016. This journal is at the top in applied mathematics (based on impact factor), being the prime publication venue for mathematically-oriented image processing research papers.
September 19, 2015 - Thomson-Reuters published their 2015 list of highly Cited Researchers, which contains about 3000 scientists from various disciplines. Three scientists from the Technion earned this distinction, and I am delighted to be one of them.
June 15, 2015 - Today I have been awarded the Henry Taub Prize for academic excellence. This prize is given annually to 4 faculty in the Technion that stand out in their research achievements.
January 1, 2015 - Starting today, I took on myself a new role in the Technion campus as the head of the prestegious Rothschild Technion Program for Excellence.
June 18, 2014 - I have been selected as a Thomson-Reuters Highly Cited Researcher. This list contains about 3000 scientists in various disciplines - see 2014 hottest researchers report for more information. The criteria for their selection is explained in details.
January 3, 2014 - Freddy Bruckstein (CS-Technion), David Donoho (Statistics-Stanford) and I have been selected the winners of the 2014 SIAG/Imaging Science Prize. The SIAM Activity Group on Imaging Science (SIAG/IS) will award the prize at the SIAM Conference on Imaging Science ( IS14, May 12-14, 2014, Hong Kong). The prize is awarded to the authors of the best paper on mathematical and computational aspects of imaging. Specifically, the committee referred to our paper, "From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images," SIAM Review 2009, recognizing us for our "fundamental contribution to the theory and practice of sparse representations and compressed sensing, and their popularization within the imaging science community.".
November 21, 2011 - Recognizing the achievements of its members is an important part of the mission of the IEEE. Each year, following a rigorous evaluation procedure, the IEEE Fellow Committee recommends a select group of recipients for one of the Association’s most prestigious honors, elevation to IEEE Fellow. I have just been informed that the IEEE Board of Directors, at its November 2011 meeting, elevated me to IEEE Fellow, effective 1 January 2012, with the following citation: "for contributions to sparsity-and-redundancy in image processing".
October 3, 2010 - In February 2009, Freddy Bruckstein, David Donoho, and I published a paper in SIAM-Review (SIAM Rev. 51: 34-81, March 2009) on sparse represnetations, covering this topic from initial theoretical ideas, and all the way to applications in image processing. Few weeks ago we have been notified that "this article has been identified by Thomson Reuters Essential Science Indicators as a featured Fast-Breaking Paper in the field of Mathematics, which means it is one of the most-cited papers in this discipline published during the past two years". Information about this article and the story behind it are now featured in Thomson Reuters ScienceWatch.
September 14, 2010 - My new book, titled "Sparse and Redundant Representations: From Theory to Applications in Signal and Image Processing", (Springer) is now available. This book provides a reader-friendly and comprehensive view of the field of sparse approxmation, and its impact to image processing. The book offers a systematic and ordered exposure to the theoretical foundations of this field, the numerical aspects of the involved algorithms, and the signal and image processing applications that benefit from these advancements. Originally written to serve as a text-book for a graduate engineering course, this book is an easy entry-point for inetrested readers, and for others already active in this area. See Amazon for more details. A Matlab package that reproduces the book's figures and contains most of the discussed algorithms is available.