Fast Artificial Neural Network Library implements multilayer artificial neural networks in C with support for both fully connected and sparsely connected networks. Cross-platform execution in both fixed and floating point are supported. It includes a framework for easy handling of training data sets. It is easy to use, versatile, well documented, and fast. PHP, Python and Mathematica bindings are available.
Version 1.2.0 adds RPROP, Quickprop and batch training in addition to the current incremental training. More activation functions have been added and shortcut connections have also been enabled. Furthermore windows dlls and Mathematica bindings have also been created.