Projecte realitzat en el marc d’un programa de mobilitat amb la Technische Universität München (TUM)

In recent years, deep learning has opened a new research line in pattern recognition tasks. It has been hypothesized that this kind of learning would capture more abstract patterns concealed in data. It is motivated by the new findings both in biological aspects of the brain and hardware developments which have made the parallel processing possible. Deep learning methods come along with the conventional algorithms for optimization and training make them efficient for variety of applications in signal processing and pattern recognition. This thesis explores these novel techniques and their related algorithms. It addresses and compares different attributes of these methods, sketches in their possible advantages and disadvantages.