Neural Network Framework is a C++ framework to develop, simulate, and analyze arbitrary complex neural networks. The programmer can use the classes provided to create neural networks with arbitrary topology and mixed type of neurons. It's very easy to add customized neurons and layers.
License: GNU General Public License (GPL)
Changes:
Saving of RealMat matrices on XML has been made prettier. Two activation functions were added: GainFunction and LogLikeFunction. A skipList parameter were added to the saveXML function in order to allow choosing of which tag to skip during saving.
More...