OpenNN is an open source class library written in C++ which implements neural networks, a classical model of artificial intelligence. This open neural networks library was formerly known as Flood. 

OpenNN has been designed to learn from both data sets and mathematical models.

Data sets:
  • Function regression.
  • Pattern recognition.
  • Time series prediction.
Mathematical models:
  • Optimal control.
  • Optimal shape design.
Data sets and mathematical models:
  • Inverse problems.

The package comes with unit testing, many examples and extensive documentation.In summary, OpenNN provides an effective framework for the research and development of neural networks algorithms and applications.

OpenNN runs on any computer platform.



OpenNN is hosted at SourceForge.


OpenNN is released under the GNU Lesser General Public License.


OpenNN contains project files for the Qt Creator IDE.


OpenNN has been built using GNU C++ and MinGW. 



OpenNN provides XML input-output by means of TinyXML2.


How to cite (APA Style):
Lopez, R. (2014). OpenNN: Open Neural Networks Library (Version 1.0) [software]. Retrieved from