What is currently available here:
		Fuzzy graph-schemes in pattern recognition. The work covers the issue of building fuzzy learning systems using decision trees. The classical approach of learning with a teacher is extended to the case when the learning set contains fuzzy data. Similarly the decision trees are generalized for the fuzzy case. The possibilities theory is consequently used. All data are specified in terms of possibility and necessity (in Russian!)
		Fuzzy machine learning framework. A library and a GUI front-end for machine learning using intuitionistic fuzzy data. The approach is based on the intuitionistic fuzzy sets and the possibility theory. Further characteristics are: fuzzy features and classes; numeric, enumeration features and features based on linguistic variables; user-defined features; derived and evaluated features; classifiers as features for building hierarchical systems; automatic refinement in case of dependent features; incremental learning; fuzzy control language support; object-oriented software design with extensible objects and automatic garbage collection; generic data base support through ODBC; text I/O and HTML output; advanced graphical user interface based on GTK+; examples of use.
		On intuitionistic fuzzy machine learning. The aim of this work is to propose an intuitionistic formulation of the machine learning problem, completely independent from probability theory. Properties of the fuzzy pattern spaces required for fuzzy inference are demonstrated.
		Software library for dealing with fuzzy things in Ada 2005. The package includes an implementation of fuzzy sets, fuzzy logical values, fuzzy numeric values (both integer and floating-point), linguistic variables, sets of linguistic variables, dimensioned fuzzy numbers and linguistic variables.

If you are interested in classical AI, I would highly recommend you Andrew W. Moore's site, especially his excellent tutorials on various methods of statistical approach. Fuzzy does not devaluate classical methods.