Università Roma Tre

The course aims to illustrate the foundation concepts underlying discriminative and generative deep neural networks.
The student will acquire the ability to employ deep networks, with particular reference to the state of the art, for the recognition and classification of images and signals, and for the generation of content, such as images and text. The fundamental techniques underlying Large Language Models, and recent prompt-based paradigms, will be explored. Applications in various domains will be illustrated, including computer vision, speech recognition, natural language analysis, machine translation. At the end of the course the student will be able to write Python code to train deep learning networks and test them in both discriminative and generative domains.