Machine Learning Methods in Visualization for Big Data tutorial

The aim of the tutorial was to show similarities between the two fields and specifically how to apply machine learning methods for data visualization purposes. The tutorial went through topics like dimensionality reduction techniques like principal component analysis (PCA), generative- and non generative models models, and MDS. It also covered clustering techniques like your good old k-means and different ways of doing hierarchical clustering. The tutorial also covered graph mining techniques, especially techniques for community finding in large (billions of nodes) graphs.

The last part of the tutorial was structured as a BYOD (bring your own data) workshop where you could get help applying the techniques from the tutorial on your own datasets. I did some initial attempts at dimensionality reduction techniques for gene expression data in the NOWAC cohort, but I still have some way to go before it’s easy to plot it in a 2D scatterplot.