At the end of the course, the student will be able to:distinguish between different types of machine learning problemsknow which technique to use to solve them and how to implement itunderstand the mathematical fundamentals of artificial neural networksuse them into a deep learning  (DL) frameworkapply the acquired knowledge to solve information and communication engineering related challengesknow the latest DL solutions in the domain of communications

The course will cover important theoretical aspects in details that are typically behind the functioning of most artificial intelligence systems and will use Python to implement the studied algorithms. 

Topics covered in the course are the following:Introduction to the courseWhat is machine learning for information and communication engineering (ICE), current applicationsFundamentals of machine learning, from problem analysis/formulation to its solution and evaluationType of data, learning problems, learning techniques and evaluation methodsNeural networksArtificial neural networks, back-propagation, gradient descent, activation functionsIntroduction to deep learning for ICERelevant network architectures, e.g., CNNs, RNNs, LSTM, TransformersDeep learning applications to ICELearning to decodeAutoencoders and their application in communicationsGenerative adversarial networks (GANs) and their application in communicationsResource allocation

Basics of linear algebra, statistics and programming.

AssignmentsOral interviewOne compensation is offered to students who failed one of the assignments.

Assignments are part of the exam. They will be given throughout the course based on the exercises and material presented during the course. Moreover, they have to be handed in within specific deadlines before the final oral exam.

Assignment grade = A, it will count as 50% of final markOral grade = O, it will count as 50% of final markFinal grade = 0.5*A + 0.5*O