Generic efficient learning algorithms to extract valuable information out of big data. Full control of the model by symbolic programming.
Python: theano, tensorflow, scikit-learn, numpy, scipy, sympy. Sage. Matlab: MatConvNet.
Books: C. Bishop "Pattern Recognition", D. MacKay "Information Theory, Inference, and Learning Algorithms"
Probabilistic modelling/analysis of systems. Especially, bio-, queue and non-parametric statistics, as well as Bayesian statistics.
R: survival, gRain, bnlearn, np, VGAM; lm, glm, isoreg. Python:statsmodels, pandas. SAMIAM. Problog.
HTML. CSS. Javascript, Coffee Script. Python: Django.
Python: regex, pyparsing. Haskell: parsec.
Atom. Vim. Pycharm. Eclipse. Jupyter.
Git. Linux.
Specialisation in probability theory and (Bayesian) statistics, for both theory and application.
Working as Python developer. Text parsing, web development and data visualisation.
Specialisation in computational neuroscience, artificial intelligence, robotics and philosophy of mind.
Making a robot using the elevator to bring a muffin.
Software: ROS, Python, C++.
Introduction to computer science and mathematics, with focus on probability theory.
Software development in Java.
Introduction into neuroinformatics and robotics, neuroscience and biology, psychology, linguistics, computer linguistics and psycho linguistics in particular, philosophy, artificial intelligence and more – in short, cognitive science.