Deep artificial neural networks applications in the biomedical sciences

Deep artificial neural networks are a family of computational models that have led to a dramatical improvement of the state of the art in several domains such as image, voice or text analysis. These methods provide a framework to model complex, non-linear interactions in large datasets, and are naturally suited to the analysis of hierarchical data such as, for instance, longitudinal data with the use of recurrent neural networks. In the other hand, the biomedical sciences are confronted with increasingly complex statistical analysis challenges that traditional methods oftentimes fail to handle properly. As deep neural networks were able to achieve so much in so little time in the field of artificial intelligence, it only feels natural to see whether these new analysis problems can be addressed with these methods. This thesis introduces the concept of deep artificial neural networks as applications in the biomedical sciences, with both a theoretical and practical approach.