The course introduces the graduate student to the mathematical concepts as well as to algorithmic techniques and computational tools in the scientific field of machine learning. More specifically, the course provides an overview of the basic supervised learning methods, namely, regression and classification models as well as non-supervised learning models that include clustering, matrix factorization, and latent semantic indexing algorithms. Following the rapid developments in the field of machine learning, modern methodologies and deep neural network architectures will also be presented. The above subjects are presented through theory lectures and practical laboratory exercises in Python programming language. The majority of the examples and applications that will be discussed within the context of the course stem from the natural processing domain and computer vision.
gioannakathenarc [dot] gr (George Ioannakis )