Fast Artificial Neural Network Library
Summary
Fast Artificial Neural Network Library is a neural network library that 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, C++, .NET, Python, Delphi, Octave, Ruby, Pure Data, and Mathematica bindings are available. A reference manual accompanies the library with examples and recommendations on how to use the library. A graphical user interface is also available for the library.
Authors
Steffen Nissen
Links
Status
incomplete information or not officially approved by the authors
Aims and scope
Mathematical Classification
Keywords
- artificial intelligence
- backpropagation
- cascade training
- computerized learning
- evolving topology training
- fixed point arithmetic
- fixed topology training
- fully connected networks
- hidden layers
- initial weights
- library
- mean square error value
- multilayer artificial neural networks
- neural connections
- neural networks
- neurons
- performance engineering
- sigmoid neural networks
- sparsely connected networks
- threshold neural networks