Machine Learning, as the most successful paradigm of Artificial Intelligence to date, has shown its great potential in restructuring all aspects in our everyday life, e.g. through decision making support, autonomous agents/vehicles, intelligent manufacturing and web-scale/social network analysis, to name a few. In this talk, I will give an overview of my recent work on kernel-based learning and neural networks as generic approaches for pattern classification. Applications related to Computer Vision problems will also be presented, as well as extensions to time series data analysis. Â