This free online workshop, designed by PRACE (Partnership for Advanced Computing in Europe), gives a practical overview of deep learning, convolutional and recurrent neural networks, GPU (graphics processing unit) computing, and neural networks. Learners are also introduced to the most common tools that exist to train and apply deep neural networks for natural language processing, images, and other applications. The training takes place over two days in the form of a series of lectures and hands-on exercises, during which participants have a chance to improve their understanding of deep learning frameworks, the cloud, the practice of using multiple GPUs, and neural networks.
This workshop is not for beginners, and as such there are some prerequisite knowledge required, including: possessing a working understanding of Python, a background in data analysis, machine learning, or a related field. No previous knowledge in deep learning is needed - but learners should still be aware of the fundamentals of machine learning, as these are not covered over the course of the training.
At the end of the workshop, students will be able to start applying deep learning to perform different tasks, utilising the GPU resources available at CSC (a virtual easy-to-use environment for working with data and programming) to deploy their own neural networks.