Fast Artificial Neural Network Library (fann)

fann is implemented in ANSI C. The library implements multilayer
feedforward networks with support for both fully connected and sparse
connected networks. Fann offers support for execution in fixed point
arithmetic to allow for fast execution on systems with no floating
point processor. To overcome the problems of integer overflow, the
library calculates a position of the decimal point after training and
guarantees that integer overflow can not occur with this decimal
point.

The library is designed to be fast, versatile and easy to use. Several
benchmarks have been executed to test the performance of the
library. The results show that the fann library is significantly
faster than other libraries on systems without a floating point
processor, while the performance was comparable to other highly
optimized libraries on systems with a floating point processor.

A user's guide accompanies the library with examples and
recommendations on how to use the library.

For documentation please see: doc/fann_doc_complete_1.0.pdf

For installation do the following:
type command: ./configure
type command: make
Now you would like to be root in order to install
type command: su
type command: make install
type command: exit
Now you are not root anymore, and you can test the library.
type command: cd examples
type command: make runtest

For further installation instructions see: INSTALL

For example programs please see:
examples/simple_train.c
examples/simple_test_float.c

For the newest version of this library please go to:
http://sourceforge.net/projects/fann/
