The FANN library is a free open source neural network library. FANN implements multilayer artificial neural networks in C with support for both fully connected and sparsely connected networks. Cross-platform execution in fixed, floating point and double precision is supported. FANN includes a framework for easy handling of training data sets, is easy to use, versatile, well documented, and fast. PHP, C++, .NET, Ada, Python, Delphi, Octave, Ruby, Pure Data and Mathematica bindings are available. A reference manual accompanies the library with examples and recommendations on how to use the library. A graphical user interface is also available for the library.
FANN was originally created by one person, but a vibrant community has evolved around the library and the FANN mailing list. The FANN community has enabled the creation of many enhancements to the library, including a graphical interface and bindings to a wide variety of other programming languages.