Deep Learning Lab

This course will introduce students to practical implementations of various deep learning models using Python and the PyTorch library. Recommended lectures are: Machine Learning, and basic courses on Linear Algebra, Analysis, Probability & Statistics. Basic knowledge of Python is expected, but it is not a hard requirement as long as the student is capable of learning it quickly. However, additional material will be provided to students that need to learn Python from scratch.

Through practical programming exercises, students will deepen their understanding of neural network based models. They will be exposed to various practical considerations that are crucial to make deep learning systems to perform well in practice.

In presenza

About 50 percent of the sessions consist of guided exercises. Different programming exercises will cover various building blocks and applications of deep learning. 

Students will be assigned four take-home assignments throughout the semester, which they are expected to complete independently and obtain some requested results. During the exam, they will present their code and some of the results they have obtained. They will also be asked specific, detailed questions about their work. The first two assignments must be submitted before the midterm, while the remaining two must be presented during the winter exam session.