Feb 13 – 14, 2019
CSC - IT Center for Science
Europe/Helsinki timezone

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 (https://keras.io/) and PyTorch (https://pytorch.org/) will be used in the exercise sessions. CSC's Notebooks (https://notebooks.csc.fi/) environment will be used on the first day of the course, and the Taito-GPU (https://research.csc.fi/taito-gpu) cluster on the second day.

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 CSC for training and deploying their own neural networks.

Prerequisites

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.  Basic knowledge of a Linux/Unix environment will be assumed.

Agenda (tentative)

Day 1, Wednesday 13.2

  •    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 networks

  •    15.00 – 16.00 Exercises: Text sentiment classification with CNNs, RNNs

Day 2, Thursday 14.2

  •    09.00 – 10.00 Lecture: GPUs, batch jobs, using Taito-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

Coffee will be served both for the morning and afternoon sessions

Lecturers: 

Markus Koskela (CSC),  Mats Sjöberg (CSC)

 

Language:  English
Price:          Free of charge

Starts
Ends
Europe/Helsinki
CSC - IT Center for Science
Training room Dogmi, 1st floor
LIfe Science Center, Keilaranta 14, Espoo, Finland

How to reach us

CSC is located in Keilaniemi, Espoo, 10 km west of the Helsinki City Center. Detailed information is available here.

Accommodation

We recommend choosing a few hotels that are most close to our premises. The nearest hotel is Radisson Blu Espoo, which is in a walking distance (only 500 m) from CSC. Another hotel close to the venue (1,8 km) is Sokos Hotel Tapiola Garden. Other hotels are located in Helsinki' downtown with a frequent and fast metro connection to Keilaniemi. Please note, that there are no special rates for participants at any hotels.

If you have any questions, please click on the support link on the left to send an e-mail to the local organizers.