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.
|Tags||Software Development Libraries Application Frameworks Scientific/Engineering Neuroscience Artificial Intelligence|
|Operating Systems||POSIX OS Independent Windows Mac OS X Unix|
Release Notes: A C binding has been implemented.
Release Notes: Two annoying bugs with saving neural networks to XML files were resolved.
Release Notes: 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.
Release Notes: Bugs in Windows compilation and installation were fixed.
Release Notes: Bugs in Random::flatInt() (when GSL is not used) and in BaseNeuralNet::randomize were fixed in this release. The Mac OS X installer doesn't require QT anymore.