Fast Artificial Neural Network Library (FANN) implements multilayer artificial neural networks in C. It is cross-platform, easy to use, versatile, well documented and fast. C++, PHP, PERL, Python, Delphi, .NET, Mathematica bindings and a GUI is available
Excellent ANN library. Fast, small, versatile, no bloat!
libfann (2.0.0) stable; urgency=low * Added Delphi bindings * Cascade training * Momentum parameter * Steepness and activation function available for single neurons * New documentation * Removed some depricated functions * New set of fann_create functions * Altered the way the callback function works * Training can be stopped by counting the number of datasets that fail instead of just MSE * Fixed a memory leak when copying training data * More activation functions * Enums used instead of integers for several parameters. * Possebility to set default logging facility * All parameters are saved to configuration file and not just the parameters needed to execute the ANN * More readable configuration file * Visual Studio .Net Project Files * Borland C++ Builder 6.0 Project files -- Steffen Nissen <sn@leenissen.dk> Fri, 06 Jan 2006 23:13:30 +0100 libfann (1.2.0) stable; urgency=low * Fixes for better compability with different compilers * Shortcut connections that skip layers * Changed version of save fileformat * fann_print_connections function * More activation functions * Batch training * RPROP training (default) * Quickprop training * fann_get_training_algorithm and fann_set_training_algorithm functions * fann_test_data function * fann_print_parameters function * Renamed some functions and variables to avoid confusion of terms (kept deprecated functions) -- Steffen Nissen <lukesky@diku.dk> Sat, 09 Oct 2004 11:13:22 +0200 libfann (1.1.0) stable; urgency=low * Error checking when allocating memory * Debian package * RPM package * Added pkg-config * Deallocate correctly in case of an error * Renamed fann_get_error to fann_get_MSE (keeping old one for now) * Renamed fann_reset_error to fann_reset_MSE (keeping old one for now) * Rearanged some code for easy access by the newly created fann php module * Defined more activation functions and documented the old (in fann_activation.h) * Customize error output * Added fann_set_error_log, fann_shuffle_train_data, fann_merge_train_data, and fann_duplicate_train_data, fann_init_weights * Added python bindings * Created DocBook XML documentation, including API reference * Rearanged files for easier development * Added MSVC++ project files -- Steffen Nissen <lukesky@diku.dk> Wed, 31 Mar 2004 21:19:32 +0200 libfann (1.0.5) stable; urgency=low * Added a new constructor * Added a callback function for output during training * Changed compile parameters for further performance * Error value not set to zero after training * Thanks to Evan Nemerson for some of these patches -- Steffen Nissen <lukesky@diku.dk> Tue, 06 Jan 2004 20:51:34 +0100 libfann (1.0.4) stable; urgency=high * Bugfix concerning default activation function -- Steffen Nissen <lukesky@diku.dk> Thu, 11 Dec 2003 12:42:41 +0100 libfann (1.0.3) stable; urgency=low * Added FANN_SIGMOID_STEPWISE activation function (faster) * Moved files around and altered some files for easyer benchmarking * Added a benchmark pdf file, benchmarking the new behavior. * Better compability with non gnu compilers (should work off the shelf) -- Steffen Nissen <lukesky@diku.dk> Tue, 09 Dec 2003 23:30:45 +0100 libfann (1.0.2) stable; urgency=low * Added configure script * Moved files around, to make the transition to configure more easy * Removed other versions of documentation than pdf -- Steffen Nissen <lukesky@diku.dk> Thu, 13 Nov 2003 11:06:47 +0100 libfann (1.0.1) stable; urgency=high * Bugfix concerning steepness parameter * Moved some files around * Added the changelog -- Steffen Nissen <lukesky@diku.dk> 3 Nov 2003 libfann (1.0) stable; urgency=high * Initial release of full functioning library -- Steffen Nissen <lukesky@diku.dk> 1 Nov 2003
Copyright © 2009 Geeknet, Inc. All rights reserved. Terms of Use
Thanks for your rating!
Would you also like to write a review?