Challenges in Deep Learning

In recent years, Deep Learning methods and architectures have reached impressive results, allowing quantum-leap improvements in performance in many difficult tasks, such as speech recognition, end-to-end machine translation, image classification/understanding, just to name a few. After a brief introduction to some of the main achievements of Deep Learning, we discuss what we think are the general challenges that should be addressed in the future. We close with a review of the contributions to the ESANN 2016 special session on Deep Learning.