Neural Network Framework icon

Neural Network Framework For Linux

3.2/5 30
GPL    

Neural Network Framework is a set of C classes and QT 4.x libraries for creating a wide variety of neural networks.. #Neural network  #C framework  #Analyze neural networks  #Neural  #Network  #C  

Description

Free Download

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:

CMakeDoxygenQT 4.x Library

� 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.

User Comments
This enables Disqus, Inc. to process some of your data. Disqus privacy policy

Neural Network Framework 1.1.5

add to watchlist add to download basket send us an update REPORT
  runs on:
Linux
  filename:
nnfw-1.1.5-src.tar.gz
  1 screenshot:
Neural Network Framework - screenshot #1
  main category:
Science and Engineering
  developer:
  visit homepage