“Making deep learning more accessible should be one of our priorities. As early adopters, the responsibility falls on us. We must make sure that no one who has the potential to use deep learning to create value gets stopped by artificial obstacles, whether a scarcity of good learning resources, or arcane and hard- to-use tools that were developed with only experts in mind. The concepts behind deep learning are simple, so why should their application be difficult ?" - Francois Chollet, creator of Keras
Machine Learning is a complicated and rapidly evolving field. Putting together the theoretical and practical skills needed to move from simple textbook examples to extracting useful information from real-world datasets can be a challenge. In this talk we present and explain a series of self-contained Machine Learning examples, focusing on understanding and managing the steps towards increased sophistication. We provide examples that illustrate methods of relevance to Precision Medicine and to medical image analysis
In the seminar, we will make use of Jupyter notebooks, which are a flexible, documentable, portable, and scalable setting for
several popular Machine Learning frameworks (including Keras/TensorFlow and PyTorch) We will interactively demonstrate Machine Learning with several Jupyter notebooks, using ordinary PCs with and without consumer graphics cards (GPUs). We will also discuss migration of Jupyter notebooks to the cloud (via Amazon AWS SageMaker), which offers state-of-the-art scaleable computing and storage for research.