7 SuperNN is an artificial neural network library, with support to arbitrary
8 feed-forward topologies, that implements state-of-the-art supervised
9 training algorithms such as Improved Resilient Backpropagation (iRprop)
10 [Igel and Hüsken, 2000] and Neuron by Neuron (NBN) [Wilamowski, Yu, 2010].
12 SuperNN is released under the LGPLv3+ license. It was tested on modern
13 GNU/Linux distributions and on MS-Windows 8 (by using MingW, VS2010, and VS2013).
15 Provides an exporter tool that allows one to generate standalone Java or C++
16 code to use trained neural networks without requiring supernn at runtime.
21 SuperNN depends on [Eigen][1] (compile time only).
33 $ cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=/usr/local ..
37 To generate the API documentation to doc/html:
39 $ doxygen doc/Doxyfile
41 To include SuperNN into your cmake project you can use the provided module located at
42 cmake/FindSuperNN.cmake.
44 You can also generate standalone Java or C++ code to run a trained neural network without requiring
45 supernn at runtime. The generators are located on the _tools_ folder.
49 Lucas Hermann Negri - lucashnegri@gmail.com - [OProj][2]
51 [1]: http://eigen.tuxfamily.org
52 [2]: http://oproj.tuxfamily.org