In this course you will learn how to build, train, evaluate and optimize a neural network using one of the most popular framework, Keras with Tensorflow backend. A typical training pipeline will be presented: data import and preprocessing, neural network training and result visualization. We aim to help you deal with some of the most frequent problems in the medical field that can be solved in a supervised manner. We will discuss data specific issues, such as label balancing, input/output representation, common medical image formats. Neural network issues such as overfitting, model and hyperparameter selection will be presented. The course will feature hands-on sessions for those of you with basic Python knowledge. We encourage each participant to bring a laptop or tablet in order to get a better grip of the concepts discussed. Only a browser and Google account is needed.