Most Popular New & Updated Top Rated Search Authors Contact Us

Linux Software › Science and Engineering › Artificial Intelligence › Fast Artificial Neural Network Library 2.1.0 Beta

Fast Artificial Neural Network Library 2.1.0 Beta

Fast Artificial Neural Network Library implements multilayer artificial neural networks in C with support for both fully connected an

Developer:	Steffen Nissen more software by author →
Price:	0.00
License:	LGPL (GNU Lesser General Public License)
File size:	0K
Language:
OS:
Rating:	0 /5 (0 votes)
Your vote:
enlarge screenshot

Fast Artificial Neural Network Library 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, Python, Delphi and Mathematica bindings are available.

Here are some key features of "Fast Artificial Neural Network Library":

Multilayer Artificial Neural Network Library in C

Backpropagation training (RPROP, Quickprop, Batch, Incremental)

Evolving topology training which dynamically builds and trains the ANN (Cascade2)

Easy to use (create, train and run an ANN with just three function calls)

Fast (up to 150 times faster execution than other libraries)

Versatile (possible to adjust many parameters and features on-the-fly)

Well documented (An easy to use reference manual, a 50+ page university report describing the implementation considerations etc. and an introduction article)

Cross-platform (configure script for linux and unix, dll files for windows, project files for MSVC++ and Borland compilers are also reported to work)

Several different activation functions implemented (including stepwise linear functions for that extra bit of speed)

Easy to save and load entire ANNs

Several easy to use examples (simple train example and simple test example)

Can use both floating point and fixed point numbers (actually both float, double and int are available)

Cache optimized (for that extra bit of speed)

Open source (licenced under LGPL)

Framework for easy handling of training data sets

Graphical Interface

C++ Bindings

PHP Extension

Python Bindings

Delphi Bindings

.NET Bindings

Mathematica Extension

Octave Extension

Ruby Bindings

Pure Data Bindings

Debian package
tags

artificial neural network library neural network are available well documented files for extra bit data sets that extra for that for easy cross platform multilayer artificial

Download Fast Artificial Neural Network Library 2.1.0 Beta

http://prdownloads.sourceforge.net/fann/libfann2_2.0.0-1_i386.deb?use_mirror=mesh

http://prdownloads.sourceforge.net/fann/libfann2_2.0.0-1_i386.deb?use_mirror=keihanna

http://prdownloads.sourceforge.net/fann/libfann2_2.0.0-1_i386.deb?use_mirror=easynews

http://prdownloads.sourceforge.net/fann/fann-2.0.0.tar.gz?use_mirror=puzzle

Authors software

Fast Artificial Neural Network Library 2.1.0 Beta (by Steffen Nissen)
Fast Artificial Neural Network Library implements multilayer artificial neural networks in C with support for both fully connected an

Similar software

annie 0.71a (by Asim Shankar)
annie stands for Artificial Neural Network Library and is a C++ API (library) for neural network training and execution.

ersions e

ASpiReNN 0.1 (by F Henry)
ASpiReNN stands for Artificial SPIking REcurrent Neural Network

Neural Net Framework 1.1 (by Pink Floyd)
NNF – Neural Net Framework is a small library, written in C language, that implements multilayer feed-forward neural networks.

Her

Java Neural Network Trainer 0.1 (by SynapticFailure)

Joone 1.2.1 (by pmarrone)
Joone is a FREE Neural Network framework to create, train and test artificial neural networks

Redland RDF Library Language Bindings 1.0.5.1 (by Dave Beckett)
Redland RDF Library Language Bindings provides high-level language bindings for the Redland RDF C libraries, allowing full access to

Python-SIP 4.5.2 (by Phil Thompson)
One of the features of Python that makes it so powerful is the ability to take existing libraries, written in C or C++, and make them

dANN 0.1-alpha-RC2 (Java) (by Jeffrey Phillips Freeman)
dANN is a library to help create artificial neural networks within other programs

AI::NeuralNet::Simple 0.10 (by Curtis Poe)
AI::NeuralNet::Simple is a simple learning module for building neural nets.

SYNOPSIS

use AI::NeuralNet::Simple;
my $net =

Other software in this category

Narval 2.0.1 (by Logilab)
A framework (language + interpreter + GUI/IDE) dedicated to the setting up of intelligent personal assistants (IPAs).

this website

Pattern Classification Program 2.2 (by Ljubomir Buturovic)
Pattern Classification Program is an open-source machine learning program for supervised and unsupervised classification of patterns

OpenAI 0.2 (by Thornhalo)
The OpenAI site is centered around an Open Source project and community involving artificial intelligence

Distributed Hardware Evolution Project (by Miguel Garvie)
The Distributed Hardware Evolution Project allows the distribution of a genetic algorithm evolving hardware designs across the Intern