Mathematical Institute for Data Science (MINDS) and Center for Imaging Sciences, Johns Hopkins
Education
20182018
Postdoctoral Fellow
Computer Science Department - Technion Israel Institute of Technology
20132018
PhD in Computer Science
Technion - Israel Institute of Technology
Advisor: Michael Elad. Topic of Thesis: From Local to Global Sparse Modeling.
20072013
Biomedical Engineering (summa cum laude)
Universidad Nacional de Entre Ríos, Argentina
Publications
Journal Papers
J. Sulam, A. Aberdam, A. Beck, M. Elad, (2018). On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networks. To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019.
Aberdam, J. Sulam, M. Elad. Multi Layer Sparse Coding: the Holistic Way. SIAM Journal on Mathematics of Data Science, 1:1, 46-77, 2019.
V. Papyan, Y. Romano, J. Sulam and M. Elad, Theoretical Foundations of Deep Learning via Sparse Representations, in IEEE Signal Processing Magazine, vol. 35, no. 4, pp. 72-89, 2018.
J. Sulam, V. Papyan, Y. Romano, M. Elad, (2017). Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning. in IEEE Transactions on Signal Processing, vol. 66, no. 15, pp. 4090-4104, 2018.
V. Papyan*, J. Sulam*, M. Elad. Working Locally Thinking Globally: Theoretical Guarantees for Convolutional Sparse Coding. IEEE Transactions on Signal Processing, 65(21), 5687-5701, 2017. * Contributed Equally.
J. Sulam, Y. Romano, R. Talmon. Dynamical system classification with diffusion embedding for ECG-based person identification.Signal Processing. Vol. 130, 403–411, 2017.
J. Sulam, M. Elad, Large Inpainting of Face Images with Trainlets, IEEE Signal Processing Letters, I. 99, 2016.
J. Sulam, B. Ophir, M. Zibulevsky and M. Elad. Trainlets: Dictionary Learning in High Dimensions. IEEE Transactions on Signal Processing, V. 64, 12, pg: 3180 – 3193, 2016
Conference Papers
E. Zisselman, J. Sulam, and M. Elad, A Local Block Coordinate Descent Algorithm for the CSC Model, to appear in CVPR 2019
J. Sulam, V. Papyan, Y. Romano, M. Elad. Projecting onto the Multi-Layer Convolutional Sparse Coding Model. ICASSP 2018 (oral presentation @ Special Session on Learning Signal Representation using Deep Learning).
V. Papyan, Y. Romano, J. Sulam, M. Elad. Convolutional Dictionary Learning via Local Processing. International Conference on Computer Vision (ICCV) 2017.
J. Sulam, R. Ben-Ari, P. Kisilev. Maximizing AUC with Deep Learning for Classification of Imbalanced Mammogram Datasets. To appear in Eurographics Workshop on Visual Computing for Biology and Medicine 2017.
J. Sulam*, Y. Romano*, M. Elad. Gaussian Mixture Diffusion. ICSEE International Conference on the Science of Electrical Engineering. Nov. 2016. *Contributed Equally.
J. Turek, J. Sulam, I. Yavne and M. Elad. Fusion of Ultrasound Harmonic Imaging with Clutter Removal Using Sparse Signal Separation. International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, April 19-24, 2015 (oral presentation).
J. Sulam and M. Elad, Expected Patch Log Likelihood with a Sparse Prior, Energy Minimization Methods in Computer Vision and Pattern Recognition EMMCVPR, January 2015 (oral presentation).
J. Sulam, B. Ophir, M. Elad, Image Denoising Through Multi-Scale Learnt Dictionaries, IEEE International Conference on Image Processing, 2014 (oral presentation).
J. Sulam, G. Schlotthauer, M.E. Torres, Nonlinear slight parameter changes detection: a forecasting approach. 41th Argentinean Workshop on Informatics JAIIO. p. 168-179, ISSN 1850-2806. August, 2012
J. Sulam, Heart rate estimation through webcam photoplethysmography. XIV Workshop on Information Processing and Control RPIC, Student Section. Oro Verde, Entre Ríos, Argentina. p. 993-997, 2011.
Invited Talks
Dec 2018 - Convolutional Networks as Sparse Enforcing Algorithms @ Integration of Deep Learning Theories workshop, NeurIPS'18.
Dec. 2017 - From Shallow to Deep Sparsity with Convolutional Networks, at the CoSIP Intense Course on Deep Learning, at the Technical University of Berlin.
Oct. 2017 - From Convolutional Sparse Coding to Deep Sparsity and Neural Networks, Seminar at the EE department of University of California San Diego.
March 2017 -Up-scaling Dictionary Learning and Theoretical Guarantees for Convolutional Sparse Coding, seminar at the Center for Imaging Science, Johns Hopkins University.
May 2015 - Up-scaling Dictionary Learning with Trainlets, Computer Vision Seminar at the Hebrew University of Jerusalem.
Awards and Distinctions
2017
Best Student Poster Award
Signal Processing Meets Deep Learning - IEEE Summer School on Signal Processing. Capri, Italy
2013
“Best Graduates from Engineering Degrees of Argentine Universities” Prize Winner
Argentinean National Academy of Engineering.
2014
Second prize at the Research Day Poster Session
Computer Science Department, Technion
for the poster Image Denoising through Multi-Scale Learnt Dictionaries.
2012
Student Paper Award
XX Jornadas de Jovens Pesquisadores AUGM. Curitiba, Brasil.
for the paper “Nonlinear time series analysis applied to the study of healthy andpathological voices”.
2011
Best Student Paper Award
XIV Workshop on Information Processing and Control RPIC2011
for the paper “Heart rate estimation through webcam photoplethysmography”
Experience
Summer 2016
IBM Research
Intern at IBM Research within the Medical Imaging Analytics group, working on machine learning and deep learning for classification of breast cancer, and within the organization team of the Digital Mammography Dream Challenge.