PRACE Deep Learning Workshop

Time: Wed 2019-03-20 08.00 - Thu 2019-03-21 17.00

Lecturer: Markus Koskela & Mats Sjöberg (CSC-Finland)

Location: Room Fantum, Lindstedtsvägen 24, F-huset, floor 5, KTH Campus

Course description

This course gives a practical introduction to deep learning, convolutional and recurrent neural networks, GPU computing, and tools to train and apply deep neural networks for natural language processing, images, and other applications.

The course consists of lectures and hands-on exercises. Keras  and PyTorch  will be used in the exercise sessions.

Learning outcome

After the course the participants should have the skills and knowledge needed to begin applying deep learning for different tasks and utilizing the GPU resources available at PDC and elsewhere for training and deploying their own neural networks.


The participants are assumed to have working knowledge of Python and a suitable background in data analysis, machine learning, or a related field. Previous experience in deep learning is not required, but the fundamentals of machine learning are not covered in this course. Basic knowledge of a Linux/Unix environment will be assumed.

Note that participants will need to bring their own laptop, and will need to have a valid account on the Beskow supercomputer system at PDC.

Schedule, registration & other details

For further details about the course and to register, please see the workshop page on the PRACE website .