PRACE Deep Learning Workshop @ KTH/PDC

Europe/Stockholm
Fantum, 5th floor (PDC, KTH Royal Institute of Technology)

Fantum, 5th floor

PDC, KTH Royal Institute of Technology

Lindstedtsvägen 24, 114 28 Stockholm, Sweden
Description

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

 

Local contacts: Dr. Lilit Axner and Dr. Kjartan Thor Wikfeldt
The agenda of this meeting is empty