Projects / Neural Network Framework

Neural Network Framework

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.

Operating Systems

Recent releases

  •  07 Jun 2008 10:39

    Release Notes: A C binding has been implemented.

    •  31 May 2008 08:54

      Release Notes: Two annoying bugs with saving neural networks to XML files were resolved.

      •  13 May 2008 16:12

        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.

        •  22 Apr 2008 09:17

          Release Notes: Bugs in Windows compilation and installation were fixed.

          •  11 Apr 2008 17:35

            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.


            Project Spotlight


            A Fluent OpenStack client API for Java.


            Project Spotlight

            TurnKey TWiki Appliance

            A TWiki appliance that is easy to use and lightweight.