Bokeh Interactive

With this notebook I want to introduce you the possibilities of Jupyter, IPywidgets and Bokeh. I think these tools in combination with Docker, Jupyter Dashboards and JupyterLab makes it very easy to create interactive processing and visualizing applications. At the moment (end 2016) some of these libraries are not very stable and might have frequent

Auto-Encoding Variational Bayes

In the last post I have introduced the probabilistic programming. The biggest problem this idea is to find an efficient approximation of the posterior for arbitrary probabilistic models. Auto-Encoding Variational Bayes (AEVB) is a great step into the right direction. Consider a dataset . It consists of i.i.d. continues samples of dimension D. The data

Introduction to Probabilistic Programming

I love the idea of Probabilistic Programming. It is basically a language to describe probabilistic models and then perform automatic inference on those models. That means that you as an expert write a simulation of your problem in a Bayesian sense. For example, a text simulation could be to first sample the number of words,

Archetypal Analysis

Recently I have read about Archetypal Analysis. It is an unsupervised learning algorithm similar to clustering analysis and dimensionality reduction. It has been introduced by Adele Cutler and Leo Breiman in 1994. In my opinion this idea doesn’t get enough attention, although there are good reasons to learn about it. The Archetypal Analysis has nice