Research Fields - Systems
Computational learning (also known as machine learning) is a rich and longstanding field of research at the intersection of computer science, statistics, optimization, and applied mathematics, and it is highly relevant and useful in various disciplines of electrical engineering. This field focuses on modeling, and on the development and analysis of prediction/discovery algorithms that enable a computer to learn/extract information about the world from examples, and to operate in a variety of computational tasks where classical approaches are not possible or sufficient. The dramatic success of machine learning-based algorithms in solving both classical and non-classical problems has made the field of computational learning one of the most prominent and in-demand areas in academia and industry.
The specialization in computational learning within the framework of advanced studies aims to train researchers with high analytical and practical proficiency in fields such as data science, machine learning, deep learning, and more. Among other topics, we study the following areas: the development and analysis of algorithms for unsupervised, supervised, and self-supervised learning problems, reinforcement learning, learning theory and understanding the generalization mechanism in learning systems, learning under privacy constraints, learning under computational constraints and trade-off analysis, and the development and analysis of fair and unbiased learning algorithms.
Researcher | Website/Laboratory Site | Research Topics |
---|---|---|
Dr. Wasim Huleihel | Website | Learning theory, High dimensional statistics, Information theory, Estimation theory, Random graphs and matrices. |
Dr.Tamir Bendory | Website | Mathematics of data science, signal processing, statistics, optimization, cryo-EM |
Dr. Roi Yehuda Livni | Website | Learning Theory, Stochastic Convex Optimization, Privacy |
Dr. Anatoly Khina | Website | Information theory, network information theory, low-delay communications, signal processing for communications, joint source–channel coding. |
Prof. Raja Giryes | Laboratory Site | Signal and image processing: theory and applications, deep learning, sparse representations, compressed sensing, low dimensional signal modeling, low-light imaging, task-driven sensing, inverse problems |
Dr. Alon Peled-Cohen | Website |
Statistical learning, online learning, bandit problems, reinforcement learning, learning to control. |
Computer vision, computer graphics, deep learning, machine learning
|
||
Dr Ilai Bistritz | Website |
Multiagent Learning, Distributed AI, Distributed Stochastic Optimization and Control, Game Theory |
Dr. Bracha Laufer-Goldshtein | Website | Signal processing, machine and deep learning, geometry-based data analysis and modeling, audio source separation and localization, reliability in modern machine learning, efficient computation. |
Prof. Ofer Shayevitz | Website | Information theory, statistical inference, estimation and learning |
Prof. Meir Feder |