Applied Deep Learning for Scientists

Deep learning is a powerful and relatively new branch of machine learning. In recent years, it has been successfully applied to some of the most challenging problems in the broad field of AI. After beating human champions in complex games like go and chess, achieving impressive levels in machine translation and conversational skills, generating photo-realistic images, and predicting protein structures at unprecedented levels of accuracy, deep learning is becoming the natural tool of choice for a broad range of data-driven scientific applications. This course will focus on practices of modern deep learning with a focus on tools and applications in life and physical sciences. It is a graduate-level introduction course that provides both the necessary theoretical background and the hands-on experience required to be an effective deep learning practitioner or to start on the path toward deep learning research.

Target group: Graduate students and postdocs across the campus.

Prerequisites: Multivariate calculus, linear algebra, probability theory.

Evaluation: Home assignments + final project

Teaching format: Lectures + recitations

ECTS: 3 Year: 2023

Track segment(s):
Elective

Teacher(s):
Alexander Bronstein Francesco Locatello

Teaching assistant(s):
Dingling Yao

If you want to enroll to this course, please click: REGISTER