Open Source Probabilistic Networks Written In Java

So just in the event that Rules engines don't cut the mustard, here's a review of Probabilistic Networks (written in Java of course) that'll help your programs do some inferencing on partial knowledge.

1. Classifier4J - Classifier4J is a Java library designed to do text classification. It comes with an implementation of a Bayesian classifier, and now has some other features, including a text summary facility.
2. jBNC -jBNC is a Java toolkit for training, testing, and applying Bayesian Network Classifiers. Implemented classifiers have been shown to perform well in a variety of artificial intelligence, machine learning, and data mining applications. Classifiers: Naive Bayes, TAN - tree augmented naive Bayes, FAN - forest augmented naive Bayes, STAN - selective tree augmented naive Bayes, STAND - selective tree augmented naive Bayes with node discarding, SFAN - selective forest augmented naive Bayes ,STAND - selective forest augmented naive Bayes with node discarding. Network Quality Measures: HGC - Heckerman-Geiger-Chickering, SB - Standard Bayesian, LC - Local criterion, LOO - Leave-One-Out cross validation, CVn,t - n -fold t-times Cross Validation
3. JavaBayes - The JavaBayes system is a set of tools for the creation and manipulation of Bayesian networks. The system is composed of a graphical editor, a core inference engine and a set of parsers.
4. BNJ - Bayesian Network tools in Java (BNJ) a software toolkit for research and development using graphical models of probability.
5. UnBBayes - UnBBayes is composed by a inference engine, a GUI editor, an API, and a learning environment. The algorithms used are based on strong junction tree method and measure and search (K2 & B.
6. VIBES - Variational Inference for Bayesian Networks. VIBES is a software package which allows variational inference to be performed automatically on a Bayesian network.
7. RISO - RISO: distributed, heterogeneous Bayesian belief networks. Belief network: a probability model defined on an acyclic directed graph; distributed: nodes can be on different hosts; and heterogeneous: allowing different types of conditional distributions.
8. SamIam - Samiam includes two main components: a graphical user interface and a reasoning engine. The graphical interface allows users to develop Bayesian network models and to save them in a variety of formats. The reasoning engine supports many tasks including: classical inference; parameter estimation; time-space tradeoffs; sensitivity analysis; and explanation-generation based on MAP and MPE.
9. HYDRA MCMC - HYDRA provides methods for implementing MCMC samplers using Metropolis, Metropolis-Hastings, Gibbs methods. In addition, it provides classes implementing several unique adaptive and multiple chain/parallel MCMC methods.
10. Naiban - Naive Bayes learning classifiers have recently gained popularity in their application to the spam vs. ham problem. By training only on misclassified data, these classifiers provide a very efficient and accurate method of classifing text. Naiban provides a learning classifier service to the Avalon/Keel framework, and comes complete with two text classifiers and a simple numeric classifier. It is easily extendable, and provides two persistance mechanisms for storing trained data.

Please, let me know what I may have forgotten.