This course provides a comprehensive overview of different concepts and methods related to deep learning. Students will first learn the foundations of deep learning, after which they will be introduced to a series of deep models: convolutional neural networks, autoencoders, recurrent neural network, and deep generative models. Students will work on case studies of deep learning in different fields such as computer vision, medical imaging, natural language processing, etc.

This course provides a comprehensive introduction to the basics of human visual system and color perception, image acquisition and processing, linear and nonlinear image filtering, image features description and extraction, classification, and segmentation strategies. Moreover, students will be introduced to quality assessment methodologies for computer vision and image processing algorithms.

The course provides a comprehensive introduction to the concepts, principles and methods of geometry-aware computer vision which helps in describing the shape and structure of the world. In particular, the objective of the course is to introduce the formal tools and techniques that are necessary for estimating depth, motion, disparity, volume, pose and shapes in 3D scenes.

This course provides a comprehensive overview of different concepts and methods related to visual object recognition and detection. In particular, the students will learn a large family of successful and recent state-of-the-art architectures of deep neural networks to solve the tasks of visual recognition, detection, and tracking.

This course provides a comprehensive introduction to digital twins. Students will learn about digital twin technology, its common applications, and benefits, how to create a digital twin for predictive analytics using sensory data fusion, primary predictive modeling methods and how to implement and interacts with a digital twin using different platforms.

This course is an introductory course on data mining, which is the process of discovering patterns in large data sets involving methods at the intersection of machine learning, statistics, and database systems.

This course is an introductory course on big data processing, which is the process of analyzing and utilizing big data. The course involves methods at the intersection of parallel computing, machine learning, statistics, database systems, etc.

This course provides a graduate-level introduction to the principles and methods of medical imaging, with thorough grounding in the physics of the imaging problems. This course covers the fundamentals of X-ray, CT, MRI, ultrasound, and PET imaging. In addition, the course provides an overview of 3D geometry of medical images and a few classical problems in medical images analysis including classification, segmentation, registration, quantification, reconstruction and radiomics.

This course provides a comprehensive introduction to using AI/ML in smart city services and applications. The course will start by reviewing basic concepts. Students will learn how to apply AI/ML to develop, design and improve smart city services. They will be able to demonstrate an understanding of the smart city concept, applications, requirements, and system design. They will develop capabilities of integrating emerging technologies in smart city components and be able to implement them. In addition, they will gain knowledge in applying security, data analytics, Internet of Things (IoT), communications and networking and work on case studies solutions for smart city infrastructures.

This course provides students with a comprehensive introduction to various trust-related issues in applications of artificial intelligence and machine learning. Students will learn about attacks against computer systems that use machine learning, as well as defense mechanisms to mitigate such attacks.

This course provides a graduate-level introduction to the principles and methods of optimization, with a thorough grounding in the mathematical formulation of optimization problems. The course covers fundamentals of convex functions and sets, first order and second order optimization methods, problems with equality and/or inequality constraints, and other advanced problems.

This course provides a comprehensive introduction to natural language processing (NLP). It builds upon fundamental concepts in mathematics, specifically probability and statistics, linear algebra, and calculus, and assumes familiarity with programming.

This course provides a comprehensive introduction to natural language processing (NLP). It builds upon fundamental concepts in NLP and assumes familiarization with mathematical concepts and programming.

This course provides a comprehensive introduction to speech processing. It builds upon fundamental concepts in speech processing and assumes familiarization with mathematical and signal processing concepts.

This course provides a comprehensive introduction to using AI/ML in Internet of Things (IoT) smart systems, services and applications. The course will start by reviewing advanced concepts. Students will learn how to apply AI/ML to develop, design and improve IoT systems and services. They will be able to demonstrate an understanding of IoT concepts, applications, requirements and system design. They will develop capabilities of integrating emerging technologies in smart IoT components and be able to implement them. In addition, they will gain knowledge and skills in applying security, data analytics, AI models, communications and networking and work on case studies solutions for IoT infrastructures.

This course is an introductory course on Information Retrieval (IR). The explosive growth of available digital information (e.g., Web pages, emails, news, Tweets, Wikipedia pages) demands intelligent information agents that can sift through all available information and find out the most valuable and relevant information. Web search engines, such as Google and Bing, are several examples of such tools. This course studies the basic principles and practical algorithms used for information retrieval and text mining. It will cover algorithms, design, and implementation of modern information retrieval systems. Topics include: retrieval system design and implementation, text analysis techniques, retrieval models (e.g., Boolean, vector space, probabilistic, and learning-based methods), search evaluation, retrieval feedback, search log mining, and applications in web information management.

This course covers the fundamentals of theoretical statistics, which are the foundation for the analysis of the properties of machine learning algorithms. Covered topics include statistical models, statistical inference, maximum likelihood estimation, optimal hypothesis testing, decision theory and Bayesian inference, non-parametric statistics, and Bootstrap, (generalized) linear model and high dimensional statistics. All necessary tools from Probability theory: deviation inequalities, type of convergence, law of large numbers, central limit theorem, properties of the Gaussian distribution (etc) will be introduced whenever needed and their proofs given at the end of each chapter.

The course covers the mathematical foundation of robotic systems and introduces students to the fundamental concepts of ROS (Robot Operating System) as one of the most popular and reliable platforms to program modern robots. It also highlights techniques to formally model and study robot kinematics, dynamics, perception, motion control, navigation, and path planning. Students will also learn the interface of different types of sensors, read and analyze their data, and apply it in various robotic applications.

As Machine Learning (ML) programs increase in data and parameter size, their growing computational and memory requirements demand parallel and distributed execution across multiple network-connected machines. In this course, students will learn the fundamental principles and representations for parallelizing ML programs and learning algorithms. Students will also learn how to design and evaluate (using standard metrics) and compare between complex parallel ML strategies composed out of basic parallel ML "aspects” and evaluate and compare between the architecture of different software systems that use such parallel ML strategies to execute ML programs. Students will also use standard metrics to explain how compilation and resource management affects the performance of parallel ML programs.

Master’s thesis research exposes students to an unsolved research problem, where they are required to propose new solutions and contribute towards the body of knowledge. Students pursue an independent research study, under the guidance of a supervisory panel, for a period of one year. Master’s thesis research helps train graduates to pursue more advanced research in their Ph.D. degree. Further, it enables graduates to independently pursue an industrial project involving research component.

This course focuses on teaching students how to develop innovative research-based approaches that can be implemented in an organization. It covers various research designs and methods, including scientific methods, ethical issues in research, measurement, experimental research, survey research, qualitative research, and mixed methods research. Students will gain knowledge in selecting, evaluating, and collecting data to address specific research questions. Additionally, they will learn design thinking skills to connect their research-based topic to practicality. After completing the course, students will have the skills to develop a full research topic that can be innovative, entrepreneurial, and sustainable and can be applied in any organization related to the topic of research.

M.Sc. Internship (up to six weeks)