The course introduces the student to the principles and methods used to solve Artificial Intelligence methods, with a particular attention to knowledge-based systems and computational logic approaches. Students will be able to correctly formulate and solve machine learning problems. Learning outcomes
Knowledge and understanding
- Provide an overview of the main techniques of machine learning: classification, regression, supervised, unsupervised and reinforcement learning - Knowledge of the Python programming language.
Applying knowledge and understanding - Solve machine learning problems starting from various data sets, by applying the techniques studied. - Use of the Python programming language.
Course Prerequisites
None
Teaching Methods
Front lectures and exercises in classroom using blackboard, projector and computer; practical activities (guided exercises). Laboratory exercises in Python using various libraries for machine learning.
Although recommended, course attendance is not mandatory.
Assessment Methods
Mandatory written/practical examination and optional oral examination.
Texts
S. J. Russel, P. Norvig: "Artificail Intelligence: A modern approach", Prentice Hall, Last or previous edition.
Contents
Introduction to Artificial Intelligence; Problem solving in AI; Knowledge Representation; Machine learning techniques in the field of artificial intelligence, such as neural networks and deep learning, discussing their properties and applicability.
