RFS: libfann v. 1.1.0
I am the upstream maintainer (and initial developer of) the Fast
Artificial Neural Network Library (fann).
I have made two debian packages for the new 1.1.0 release and I would
very much like them to be a part of the main debian archive. For this I
will need a sponsor.
The packages are:
As far as I know the packages have been built according to all the
debian policies, but since they are my first debian packages, then what
do I know (lintian doesn't complain though).
A description of the fann library follows here:
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.
* Multilayer Artificial Neural Network Library in C
* Backpropagation training
* Easy to use (create, train and run an ANN with just three
* Fast (up to 150 times faster execution than other libraries)
* Versatile (possible to adjust many parameters and features
* Well documented (An easy to use reference manual and a 50+ page
university report describing the implementation considerations
* Cross-platform (configure script for linux and unix, project
files for MSVC++ and Borland compilers are also reported to
* Several different activation functions implemented (including
stepwise linear functions for that extra bit of speed)
* Easy to save and load entire ANNs
* Several easy to use examples (simple train example and simple
* Can use both floating point and fixed point numbers (actually
both float, double and int are available)
* Cache optimized (for that extra bit of speed)
* Open source (licenced under LGPL)
* Framework for easy handling of training data sets
* PHP Bindings
* Python Bindings
* RPM package
* Debian package