Back in 2008 I released a small software package for the estimation of the mutual-information from data. This toolbox (essentially a collection of software-tools that I was using for my research work) attracted quite some interest within the neuroscience community to which it was aimed.

Receiving feedback from users all around the world, I started to realize how hard it was for people without a strong background in statistics and information-theory to apply numerical-information-theory techniques to actual data. The problem, however, did not lie with the users, but rather with the required information being scattered over a multitude of extremely technical papers comprehensible only to few specialized scholars.

However, it is my belief that the fundamental concepts behind numerical-infor-mation-theory techniques and their applications can be presented in an intuitive, easy-to-understand way accessible also to non-experts. Everyone can learn to apply these methods correctly and analyze critically their results without having to attain a degree in statistics.

This guide aims at providing a straightforward introduction to the fundamental concepts of numerical-information-theory with tips-and-tricks for the estimation of the information quantities from actual data. The guide also serves as an step-by-step manual for the new toolbox (the \texttt{InfoToolbox}), a software suite that aims at providing an exhaustive and unified set of user-friendly numerical information-theory tools for a variety of computational environment.