Neural Network Framework 1.1.5

Neural Network Framework is a set of C classes and QT 4.x libraries for creating a wide variety of neural networks.
Neural Network Framework
  1 Screenshot
Neural Network Framework is a set of C classes and QT 4.x libraries for creating a wide variety of neural networks. The framework is structured at different levels of complexity, in order to provide various interfaces for quick-easy and deep-expert utilizations:

at the lowest level it's possible to act completely free of restrictions for building complex architectures; from this level expert-users can contribute to NNFW adding new functionalities;
in the intermediate level there are classes for quick-creation of common neural networks such as the multilayer feed-forward network, simple recurrent networks (e.g. Elman, Jordan), Radial-basis network and so on;
the possibility to represent a neural network with XML files, allows for an abstract and general interface for accessing all the functionalities of the NNFW;
a graphical interface it's the high level method to use the framework; this is the most user-friendly and easy method for users, and a way to fool around with complex neural networks.

Requirements:

CMake
Doxygen
QT 4.x Library

Compiling NNFW on Linux

Download the source package and unpack it where you want;
Open your preferred console and move to the directory where NNFW has been unpacked;

Quick procedure

Launch follow commands:

$> cmake .
$> make
$> make install

The library will be installed in the /usr/local directory

Normal procedure

Launch the program ccmake:

$> ccmake .

Configure the NNFW_CONFIG variable to fits your needs; (see Configuring the NNFW )
Press the "c" key on the keyboard to check the pre-compiling configuration's parameters (please consider that default parametrs should works correctly);
Press the "g" key on the keyboard to generate the Makefile and return to the Terminal;
Launch the command "make" to compile the library;
A file named "libnnfw.a" will be created in lib directory of source tree;
Now with "make install" the library will be installed in the PREFIX directory configured by ccmake.

Recommended procedure (out-of-sources building)

Suppose that you unpacked sources in directory /some/place/nnfw-src/
Create a subdirectory called build: /some/place/nnfw-src/build
Move to build directory and from there launch ccmake:

$> ccmake ../

Configure the NNFW_CONFIG variable to fits your needs; (see Configuring the NNFW )
Press the "c" key on the keyboard to check the pre-compiling configuration's parameters (please consider that default parametrs should works correctly);
Press the "g" key on the keyboard to generate the Makefile and return to the Terminal;
Launch the command "make" to compile the library;
A file named "libnnfw.a" will be created in lib directory of build tree;
Note that all stuffs generated by CMake and Make procedures are localized into the build directory; so the main source tree is kept clean!
Now with "make install" the library will be installed in the PREFIX directory configured by ccmake.

What's New in This Release:

A C binding has been implemented.

last updated on:
June 8th, 2008, 15:31 GMT
price:
FREE!
developed by:
G. Massera
homepage:
www.nnfw.org
license type:
GPL (GNU General Public License) 
category:
ROOT \ Science and Engineering \ Neuroscience
Neural Network Framework
Download Button

In a hurry? Add it to your Download Basket!

user rating 30

3.2/5
 

0/5

Rate it!

Add your review!

SUBMIT