Start: Thursday, 17 December 2020 @ 07:00

End: Friday, 18 December 2020 @ 14:00

Description:

This course will be delivered as an ONLINE EVENT for remote participation due to the COVID-19 measures enforced by most European governments.

THE COURSE IS FULLY BOOKED! If you have registered to this course and you are not able to attend, please cancel your registration in advance. We have processed a LIMITED WAITING LIST. Please send your requests on cancellation/wait list to patc@csc.fi. We will keep those on the waiting list informed of whether participation will be possible. Please note that the wait list is at a first come, first served basis.

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 the GPU-accelerated Puhti supercomputer 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, Thursday 17.12

   09.00 – 11.00 Introduction to deep learning and to Notebooks


   11.00 – 12.00 Multi-layer perceptrons

               12:00 - 13:00  Lunch

   13.00 – 14.30 Image data and convolutional neural networks


   14.30 – 16.00 Text data and recurrent neural networks

Day 2, Friday 18.12

   09.00 – 10.30 Deep learning frameworks, GPUs, batch jobs


   10.30 – 12.00 Image classification exercises

               12:00 - 13:00  Lunch

   13.00 – 14.30 Attention and text categorization exercises


   14.30 – 16.00 Cloud, using multiple GPUs

Lecturers: 

Markus Koskela (CSC),  Mats Sjöberg (CSC)

Language:  English
Price:           Free of charge (2 training days)

REGISTRATION is OBLIGATORY since the details to access the online course will be provided to the registered and accepted attendees only. If you have registered to this course and you are not able to attend, please CANCEL your registration in advance by sending an email to patc@csc.fi
https://events.prace-ri.eu/event/1087/

Event type:
  • Workshops and courses
[ONLINE] Practical Deep Learning @ CSC https://tess.elixir-europe.org/events/online-practical-deep-learning-csc This course will be delivered as an ONLINE EVENT for remote participation due to the COVID-19 measures enforced by most European governments. THE COURSE IS FULLY BOOKED! If you have registered to this course and you are not able to attend, please cancel your registration in advance. We have processed a LIMITED WAITING LIST. Please send your requests on cancellation/wait list to patc@csc.fi. We will keep those on the waiting list informed of whether participation will be possible. Please note that the wait list is at a first come, first served basis. 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 the GPU-accelerated Puhti supercomputer 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, Thursday 17.12    09.00 – 11.00 Introduction to deep learning and to Notebooks    11.00 – 12.00 Multi-layer perceptrons                12:00 - 13:00  Lunch    13.00 – 14.30 Image data and convolutional neural networks    14.30 – 16.00 Text data and recurrent neural networks Day 2, Friday 18.12    09.00 – 10.30 Deep learning frameworks, GPUs, batch jobs    10.30 – 12.00 Image classification exercises                12:00 - 13:00  Lunch    13.00 – 14.30 Attention and text categorization exercises    14.30 – 16.00 Cloud, using multiple GPUs Lecturers:  Markus Koskela (CSC),  Mats Sjöberg (CSC) Language:  English Price:           Free of charge (2 training days) REGISTRATION is OBLIGATORY since the details to access the online course will be provided to the registered and accepted attendees only. If you have registered to this course and you are not able to attend, please CANCEL your registration in advance by sending an email to patc@csc.fi https://events.prace-ri.eu/event/1087/ 2020-12-17 07:00:00 UTC 2020-12-18 14:00:00 UTC [] [] [] workshops_and_courses [] []