This course provides a broad introduction to machine learning and pattern recognition. The course will cover different topics ranging from supervised learning (parametric/non-parametric algorithms, kernel methods, feedforward neural networks), unsupervised learning (clustering, dimensionality reduction, autoencoders, deep generative models), and reinforcement learning. In the final part of the course, some applications of machine learning will be presented in the fields of computer vision, robotics, and natural language processing. Theoretical discussion will be complemented with labs in Python using open-source libraries.
At the end of the course, students will know the theoretical bases and the main algorithms for machine learning, and will know how to apply such algorithms to pattern recognition problems and automated data analysis.
All the course material is available (for UNITN students) on Moodle (course "Introduction to machine learning [146315]").