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 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.

Agenda (tentative)

Day 1, Thursday 12.12

   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, recurrent neural networks, and attention

Day 2, Friday 13.12

   09.00 – 10.30 Deep learning frameworks, GPUs, batch jobs


   10.30 – 12.00 Image classification exercises


   12.00 – 13.00 Lunch


   13.00 – 14.00 Text categorization exercises


   14.00 – 16.00 Cloud, 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
https://events.prace-ri.eu/event/941/