OpenNN is a class library written in C++ which implements neural networks.
The library is intended for advanced users, with high C++ and machine learning skills. OpenNN provides an effective framework for the research and development of data mining and predictive analytics algorithms and applications.
OpenNN is based on the most popular neural network model, the multilayer perceptron. The package comes with unit testing, many examples and extensive documentation.
The library has been designed to learn from data sets. Some typical applications here are function regression (modelling), pattern recognition (classification) and time series prediction (forecasting).
OpenNN is being developed by Intelnics, a company specialized in the development and application of neural networks.
- Extensive documentation.
- Unit testing.
- Many examples.
It a shame it is not as popular as FANN. Terrific library. Found a bug with unscaling output that took me 11 hrs of work, yet still happy. I have reported it. Just in case: neural_network.cpp :line847: if(!unscaling_layer_flag) should be if(!unscaling_layer_pointer)
fast download and works, recommended.