The main goal of this course is to introduce students to the basic and some advanced approaches, trends and tools in the field of machine learning systems. Students will also be able to develop machine learning systems intended to be used within embedded electronic systems.

Students who successfully complete this course should be able to follow the latest results, as well as to understand the latest technical and scientific literature in this field. Beside theoretical knowledge, students will also gain experience in using contemporary design tools used to develop machine learning systems. Students will also be able to develop artificial intelligence systems, based on machine learning, that will be used in embedded systems.

Introduction to machine learning. Formal learning model. Model selection and validation. Regularization and stability. Linear predictors. Support vector machines. Kernel methods. Decision trees. Artificial neural networks. Online learning. Incremental learning. Adaptive learning. Clustering. Dimensionality reduction. Feature selection. Generative models. Reinforcement learning. Deep learning. Ensemble learning. Machine learning implementation techniques targeting embedded systems. Hardware accelerators for machine learning.

Lectures; Auditory Practice; Computer Practice; Laboratory Practice; Consultations.