CSC's trainings and events have moved

Find our upcoming trainings and events at www.csc.fi.

This site is an archive version and is no longer updated.
 

Go to CSC Customer trainings and Events

practical_dl_sep2019

Practical Deep Learning
Date: 12.09.2019 9:00 - 13.09.2019 16:00
Location details: The event is organised at the CSC Training Facilities located in the premises of CSC at Keilaranta 14, Espoo, Finland. The best way to reach us is by public transportation; more detailed travel tips are available.
Language: english-language
lecturers: Markus Koskela (CSC)
Mats Sjöberg (CSC)
Price:
  • 120 for-finnish-academics
  • 560 for-others
The fee covers all materials, lunches as well as morning and afternoon coffees.
The seats are filled in the registration order. If a cancellation is received five (5) business days prior to the course, the course fee will be refunded with the exception of a handling fee of 10 €. For no-shows and cancellations after the cut of date no refunds will be made. Registration can be transferred to someone else from the same organization without additional charge.

Payment can be made with electronic invoicing, credit card, or direct bank transfer. Note that for electronic invoicing you need the operator and e-invoicing address (OVT code) of your organization. Please also note that invoice reference is needed for electronic invoicing in your organization, so please have this available when registering.
Additional Information
Content: mats.sjoberg@csc.fi
Practicalities: event-support@csc.fi

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. TensorFlow 2, Keras, and PyTorch  will be used in the exercise sessions. CSC's Notebooks environment will be used on the first day of the course, and Taito-GPU and the new Puhti-AI partition 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.

 

Program

Day 1

9-11 Introduction to deep learning and to Notebooks
11-12 Multi-layer perceptrons
12-13 Lunch
13-14:30 Image data and convolutional neural networks
14:30-16 Text data, recurrent neural networks, and attention

Day 2

9-10:30 Deep learning frameworks, GPUs, batch jobs
10:30-12 Image classification exercises
12-13 Lunch
13-14 Text categorization exercises
14-16 Cloud, using multiple GPUs