Abstract

Abstract: I strongly believe in being able to use the right tool for the right job. The .NET platform has allowed me to achieve exactly that: I’ve chosen to write most of my own code in F#, a language which gives me the flexibility to code in a functional, imperative and object-oriented style. dnAnalytics, the open source numerical library I use from F#, is written in a mix of C# and C. Whenever I need to do rapid prototyping or glue together an experiment, I script it in either Python or F#. The key enabler is the .NET platform: it makes sure that all these languages understand each other. In my presentation I want to elaborate on dnAnalytics and how you can use it in your own research. dnAnalytics contains many essential tools for scientific computing: numerical linear algebra, special function evaluation, statistical tests, various distribution classes and much more. Using a short interactive demo I will highlight some of the key features of dnAnalytics.

Biography: After receiving an undergraduate degree in computer science from Leuven, I started a Master’s degree at the University of Wisconsin where my research was focused on applying statistical machine learning techniques to problems in natural language processing. In 2007, I joined the machine learning group at the University of Cambridge where my research shifted to developing new algorithms and techniques for probabilistic modeling. More recently, I have been involved in a project to build a tool that makes probabilistic machine learning more accessible to the data mining community. Since the start of my PhD I have been actively contributing to dnAnalytics: an open source numerical library for the .NET platform.