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
