A number of the Machine Learning nodes work by calling third party softwares, including Weka, MLlib, DL4J, while others were written specifically for Pyramid. When adding a Machine Learning node to the Data Flow, you won't get the complete properties. Rather, you'll need to set your preferences in the limited Properties panel, and Pyramid will then call the relevant software.
Waikato Environment for Knowledge Analysis (Weka) is a machine learning software written in Java (making it fast). In Pyramid, it’s used for clustering, classification, and regression.
Apache Spark's MLlib is a machine learning library written in Scala. It can perform functions on very large amounts of data. MLlib is used in Pyramid for clustering and classification algorithms.
Deep Learning for Java is used for the Shallow Neural Net script.
The remaining machine learning scripts are written in Pyramid. These are very efficient, because they were built specifically for Pyramid.
If you want to use scripts, you can either use the Marketplace, which supports both R and Python (which you can tweak), or you can create your own script and save it for future use. Both of these options are available from the Scripting panel.