Advanced Deep Learning: The Transformer Architecture Learning

During the course, we will see advanced DL algorithms, such as the Transformer. We will code it from scratch in PyTorch. Then we will learn how to leverage more high-level API to train and fine-tune transformer-based models to solve specific tasks in NLP and not only. We will also taste some Interpretability/Explainability methods and apply them to the tasks we previously solved.

Lecturer(s)

placeholder person image
Lecturer
Alberto Cazzaniga
Researcher at the Research and Innovation Technology Institute (RIT)