Fast Artificial Neural Network Library

52 Recommendations
609 Downloads (This Week)
Last Update:
Download FANN-2.2.0-Source.zip
Browse All Files
Windows BSD Linux

Screenshots

Description

Fast Artificial Neural Network Library is a free open source neural network library, which 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. Bindings to more than 15 programming languages are available. An easy to read introduction article and a reference manual accompanies the library with examples and recommendations on how to use the library. Several graphical user interfaces are also available for the library.

Fast Artificial Neural Network Library Web Site

Update Notifications





User Ratings

 
 
52
7
Write a Review

User Reviews

  • Posted by Salvador Abril 2012-10-26

    Nice project! You did a great job. Thank you!

  • Posted by Ali Ibrahim 2012-11-23

    I have reviewed this library and OpenNN (flood), for a project of mine. OpenNN may appear not as popular as FANN. FANN has more add-ons. But openNN already has this built-into it. API for openNN is much nicer. Both have their share of bugs, but debugging a C code is much more annoying. Plus this looks already abandonned v3 as the upcoming release for 3 years, we has 2.1beta and 2.2

  • Posted by Maria 2012-09-12

    The only tool needed - a must have. This a super cool project

  • Posted by wupix 2012-04-08

    Nice and Easy to use.

Read more reviews

Additional Project Details

Languages

English

Intended Audience

Developers, Education, Science/Research

User Interface

Web-based, Win32 (MS Windows), X Window System (X11)

Programming Language

C, C#, C++, PHP, Perl, Python

Registered

2003-10-28

Icons must be PNG, GIF, or JPEG and less than 1 MiB in size. They will be displayed as 48x48 images.