annie is a C++ API (library) for neural network training and execution. It can be linked to both Windows and Linux applications. Support for multi-layer perceptron networks, radial-basis networks, and Hopfield Networks is present. It can also be interfaced with Matlab's Neural Network toolbox.
ca-ga is a toy artificial life simulation that uses genetic algorithms on large cellular automata. It uses simple but easily extended DNA that is 8k long by default, though you can take the size out to anything you have time to evolve. It sits under each cell of a 128x128 board and orders operations to transfer energy in the hopes of achieving a kill and breed. The simulation features a mutating fitness function, emergent sex, and a proof of concept real world fitness function. After enough generations, the cells or genes could achieve collectivism and organismhood, coordinating the values of the hotspots that determine board temperature in order to maintain a desired equilibrium. But maybe not. If you work in a fitness function, an optimizing problem solver results.
clipsmm is a C++ library that provides an interface to the CLIPS library. CLIPS provides a C environment for the construction of rule- and/or object-based expert systems used by NASA, branches of the military, numerous federal bureaus, government contractors, universities, and many companies. Several areas in which clipsmm extends the CLIPS interface are templated function callbacks using sigc++ slots, and encapsulated CLIPS execution environments.
dbacl is a digramic Bayesian text classifier. Given some text, it calculates the posterior probabilities that the input resembles one of any number of previously learned document collections. It can be used to sort incoming email into arbitrary categories such as spam, work, and play, or simply to distinguish an English text from a French text. It fully supports international character sets, and uses sophisticated statistical models based on the Maximum Entropy Principle.