Deep learning has rapidly become a de facto standard for many AI tasks in numerous market segments on platforms ranging from mobile devices to supercomputers. The course will focus on basic notions in deep learning, deep network architectures, training regimes and algorithms, concepts of hardware accelerators, and a lot of hands-on coding.
Digital imaging and image processing has become an inseparable part of our reality, profoundly impacting our social communication skills. The purpose of this course is a self-contained introduction to modern techniques in image processing. We will understand concepts involved in acquiring, sampling, representing, compressing, and processing of multi-dimensional signals (images and videos). We will discuss the notion of inverse problems and ways to solve them — from traditional prior-based methods to modern learning-based methods. Finally, apart from the standard image acquisition model, we will also look at more exotic computational and medical imaging schemes and understand the challenges and applications involved therewithin.