This workshop 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. It consists of lectures and hands-on exercises. Keras (https://keras.io/) and PyTorch (https://pytorch.org/) will be used in the exercise sessions. 

After the workshop 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 for training and deploying their own neural networks.

The participants are assumed to have working knowledge of Python and 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 on this course.

Agenda

            Time


        Day 1 / March 20, 2019    




        09:00-10:30


        Lecture: Introduction to deep learning




        10:30-11:00

        Exercises: Introduction to Notebooks, Keras fundamentals



        11:00-12:00


        Lecture: Image data, multi-layer percepton networks, convolutional neural networks




        12:00-13:00


        Lunch




        13:00-14:00


        Exercises: Image classification with MLPs, CNNs




        14:00-15:00

        Lecture: Text data, embeddings, neural NLP, recurrent neural network


        15:00 - 16:00

        Exercises: Text sentiment classification with CNNs, RNNs

            Time


        Day 2 / March 21, 2019    




        09:00-10:00

        Lecture: GPUs, batch jobs, using PDC-GPU



        10:00-12:00

        Exercises: Image classification



        12:00-13:00


        Lunch




        13:00-14:00


        Exercises: Text categorization and labelling




        14:00-15:00

        Lecture: Cloud, GPU utilization, multiple GPUs


        15:00-16:00

        Exercises: Using multiple GPUs

Pre-requisites:

1. Own laptop;
2. Valid account at PDC, KTH. After getting an acceptance confirmation you have to apply for a PDC account on Beskow supercomputer. The instructions how to apply for the account will be sent by the confirmation e-mail.

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

Language: English
Price:          Free of charge
 
https://events.prace-ri.eu/event/412/