The course offers an introduction to practical deep learning.This includes teaching you important concepts about deep learning and how to implement them using PyTorch framework.Through this course, you will learn theoretical concepts and apply them to solve real practical problems.

Theoretical concepts about deep learning will be explained and discussed along with how to implement them.Solutions proposed by students for each homework will be presented and discussed.As deep learning is an empirical science, there will be plenty of room for discussion of your observations.

Linear Algebra/Calculus/ProbabilityLinear RegressionMulti Layers PerceptronsConvolutional Neural NetworkGenerative MethodsRecurrent Neural NetworksComputer VisionsNatural Language Processing

Python 3

Goodfellow I. J., Bengio Y., Courville A. C. (2016): Deep Learning. MIT Press http://www.deeplearningbook.org/Aston Zhang A., Lipton, Z.C., Li M., & Smola A.J. (2020) Dive into Deep Learning 

During the semester, multiple at-home mini-projects will be given to the students. One student will then be randomly selected to present his solution to the classroom, following a discussion session.Grades will be composed of the quality of the solutions proposed.

Deep Learning with Pytorch.Propose a Deep Learning solution to a Kaggle problem.

At home + oral presentation