Academic Year 2023-2024



Giuseppe Serra
Unit Credits
Teaching Period
First Period
Course Type
Prerequisites. Knowledge of programming techniques and basic mathematics.
Teaching Methods. Lectures, exercises, and laboratory.
Verification of Learning. The exam consists of a written test and an oral discussion.
Capacità relative alle discipline

1.1 Knowledge and understanding: During the course, the student will learn basic knowledge of the main components used for neural network development and their learning strategies. He will also learn procedures for evaluating and analyzing the obtained results.

1.2 Applied knowledge and understanding: the laboratory activity allows the student to consolidate the theoretical knowledge, presented during the lectures, through their use in real application cases.

Capacità trasversali/soft skills

2.1 Autonomous assessments: the student will acquire theoretical and practical skills that will allow him to develop Deep Learning systems algorithms and to analyze critically the obtained results.

2.2 Communication skills: the student will learn appropriate terminology and he will be able to present the main features of Deep Learning architectures and algorithms presented in the course.

2.3 Learning skills: the course aims to provide students with the basic knowledge needed to understand and solve automatically machine learning problems using critically Deep Learning techniques.

The course aims to present architectures and algorithms in order to design, implement and train Artificial Neural Networks. Deep Learning is subfield of Machine Learning and it is a branch of Artificial Intelligence which refers to systems and algorithms inspired by the structure and function of the brain called Artificial Neural Networks.

Recently, thanks to the increasing amount of data digitally available, Machine Learning, and Deep Learning in particular, has become an important field of computer science with several applications in different scientific areas such as bioinformatics, medicine, natural language processing, computer vision, speak recognition, autonomous driving systems, and so on.

The course aims to enable students to acquire basic knowledge to solve machine learning tasks through a proper formulation of the problem, a critical choice of the neural network architecture and an experimental analysis of the obtained results. The course includes laboratory activities so that students can directly test on real applications concepts learned in class.

Scientific papers, reports, slides, etc available in the E-Learning portal.