Thomas Abeel

This release fixes bugs in clustering algorithms where some algorithms could return empty clusters in some cases.

Some minor improvements around the library: made some more methods to manipulate datasets and methods to compare arrays.

New implementation of the Adaptive Quality Based Clustering algorithm based on the original implementation in Matlab.

A (nearly) complete Ant script to make a release is now in the SVN repository.

In this release we cleaned some more in the code of SOM and AQBC, we especially removed a lot of redundant variables.

We fixed a bug in the KMeans algorithm that made the algorithm return an empty cluster in some cases. This also affected the variants of KMeans: IterativeKMeans, MultiKMeans and IterativeMultiKMeans.

This release of the Java Machine Learning API offers several improved algorithms. Besides several improvements we have also added a new algorithm: Self-Organizing Maps (SOM) to the list of clustering algorithms. We have updated the AQBC algorithms with some modifications to avoid situations where the algorithm could not converge. For full details see the changelog