LINUX CATEGORIES:



NEWS ARCHIVE >>
SOFTPEDIA REVIEWS >>

7-DAY TOP DOWNLOAD

#
Program
Chromium OS 0.4.22.8
4,182
BackTrack 3.0 / 4.0
Pre-Final

3,337
Wine 1.0.1 / 1.1.33
2,588
VLC 1.0.3
2,571
Yahoo Messenger
1.0.4

2,245
Chrome OS 0.4.237
Beta

2,095
Ubuntu 9.10
1,913
Thunderbird PST
Import plugin 1.2

1,657
Adobe Flash Player
for Linux 10.0.32.18
/ 10.1 Beta

1,544
Fedora 12
1,518

WEEK'S BEST

  • Ubuntu 9.10
  • Ubuntu Netbook Rem...
  • Pidgin 2.6.3
  • Wine 1.0.1 / 1.1.33
  • Linux Kernel 2.6.3...
  • Mozilla Firefox 3....
  • Fedora 12
  • OpenOffice.org 3.1.1
  • Firestarter 1.0.3
  • The Gimp 2.6.7 / 2...
  • FileZilla 3.3.0.1
  • Transmission 1.76
  • Super Grub Disk 0....
  • Gufw 9.04.2
  • Skype 2.0.072 / 2....
  • openSUSE Linux 11.2
  • Opera 10.10 Final
  • Adobe Flash Player...
  • wine-doors 0.1.3
  • Google Gadgets 0.1...
  • Home / Linux / Science and Engineering / Neuroscience

    Neural Network Framework 1.1.5

    Download button

    Downloads: 1,597  Add to download basket  Tell us about an update
    User Rating:
    Rated by:
    Good (3.0/5)
    26 user(s)
    Developer:

    License / Price:

    Last Updated:

    Category:
    G. Massera | More programs
    GPL / FREE
    June 8th, 2008, 15:31 GMT
    ROOT / Science and Engineering / Neuroscience

     Read user reviews (0)  Add a review  Refer to a friend  Subscribe

     

    Neural Network Framework description

     

    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 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.

      


    TAGS:

    neural network | C framework | analyze neural networks | neural | network | C



    HTML code for linking to this page:


    Go to top

    Windows tabGames tabDrivers tabMac tabLinux tabScripts tabMobile tabHandheld tabGadgets tabNews tab

    SUBMIT PROGRAM   |   ADVERTISE   |   GET HELP   |   SEND US FEEDBACK   |   RSS FEEDS   |   ENTER NEWS SITE   |   ENGLISH BOARD   |   ROMANIAN FORUM