The course aims to provide knowledge and skills in modern techniques and tools for machine learning, to create an understanding of its uses, strengths, and weaknesses. All in order to then apply these skills in a real world application. After the course, you will be able to:- describe basic terms, methods and approaches for machine learning- compare and argue for and against different types of machine learning methods for different application areas- use basic methods and various tools for machine learning- apply these techniques in a real world application as well as reflect and evaluate the results Course Content- Basic terms, methods and approaches for machine learning- Overview of different types of machine learning algorithms- Uses, strengths and weaknesses of the various types of machine learning- Overview of common tools and their applications- Neural networks (NN), convolutional neural network (CCN), recurrent neural networks (RNN), long short term memory (LSTM)- Machine learning project The course consists of a few lectures, a web-based theory exam, a series of laboratory exercises and a project assignment. The lectures present the necessary theory, tools, algorithms and basic terms, etc. The web-based theory exam consists of a quiz intended to examine basic terms and understanding. The labs are intended to provide basic skills and tools for machine learning. Finally, in the project, the student will demonstrate their own work on machine learning to merge previous knowledge. Depending on the student's previous experience in machine learning and programming ability, the work effort is estimated to be 80 hours of work.