The COMPUTE course "Introduction to Deep Learning" (4.5 ECTS) is now open for registration.  The course will run during September and October 2020.  Details of the course content can be found below and on the COMPUTE webpage. The application form can be found here.

Students must be COMPUTE members to take this course: Membership is free, comes without any obligatory courses etc., and is open to all PhD students at the faculties of Science, Medicine, and LTH. The membership application form can be downloaded here.

------------------------------------------------------------

Introduction to deep learning (4.5 ECTS)

Recent development in machine learning have led to a surge of interest in artificial neural networks (ANN). New efficient algorithms and increasingly powerful hardware has made it possible to create very complex and high-performing ANNs. The process of training such complex networks has become known as deep learning and the complex networks are typically called deep neural networks.

The aim of this course is to introduce students to common deep learnings architectues such as multi-layer perceptrons, convolutional neural networks and recurrent models such as the LSTM. Basic concepts in machine learning till also be introduced. The course consists of a series of lectures and computer exercises. The programming environment will be python (Jupyter notebook) together with the deep learning libraries Keras and Tensorflow.

The course will be given in flipped classroom mode, with students watching recorded lectures and taking part in discussion sessions. Face-to-face sessions will take place following the schedule below. If necessary these will take place over zoom.

Schedule and content:

     14/9, 13.15 - 14.00   Introduction to the course
     18/9, 13.15 - 14.00   The Jupyter notebook and Keras
     23/9, 13.15 - 15.00   The MLP
     25/9, 13.15 - 15.00   CNN, part 1
     1/10, 13.15 - 14.00   CNN, part 2
     2/10, 13.15 - 14.00   Autoencoder and GAN
     7/10, 13.15 - 15.00   Recurrent networks
    15/10, 13.15 - 15.00   Presentations of project work
    16/10, 13.15 - 15.00   Presentations of project work

The literature will consist of parts from the deep learning book and lecture
notes.

Course responsible: Mattias Ohlsson

Teachers: Mattias Ohlsson, Patrick Edén + additional teachers and guest
lecturers