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, Delphi and Mathematica bindings are available.
· Multilayer Artificial Neural Network Library in C
· Backpropagation training (RPROP, Quickprop, Batch, Incremental)
· Evolving topology training which dynamically builds and trains the ANN (Cascade2)
· Easy to use (create, train and run an ANN with just three function calls)
· Fast (up to 150 times faster execution than other libraries)
· Versatile (possible to adjust many parameters and features on-the-fly)
· Well documented (An easy to use reference manual, a 50+ page university report describing the implementation considerations etc. and an introduction article)
· Cross-platform (configure script for linux and unix, dll files for windows, project files for MSVC++ and Borland compilers are also reported to work)
· 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 test example)
· 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
· Graphical Interface
· C++ Bindings
· PHP Extension
· Python Bindings
· Delphi Bindings
· .NET Bindings
· Mathematica Extension
· Octave Extension
· Ruby Bindings
· Pure Data Bindings
· Debian package
· Ограничения Fast Artificial Neural Network Library 2.1.0 Beta
Ограничения не определены
· Специальные требования Fast Artificial Neural Network Library 2.1.0 Beta
Специальные требования не определены
· История версий и изменений Fast Artificial Neural Network Library
История пуста
· Описание и дополнения от редакторов и пользователей сайта