Neural Nets

The extended Kalman filter can not only estimate states of nonlinear dynamic systems from noisy measurements but also can be used to estimate parameters of a nonlinear system. A direct application of parameter estimation is to train artificial neural networks. This function and an embeded example...

This is a learning model for matrix-based data. It can be more efficient than standard vector-based models when the training sample is small or the inputs are matrices, since this model has less parameters than standard ones and exploits an inner structure of the inputs. This model can be...

We introduce an algorithm based on the morphological shared-weight neural network. Being nonlinear and translation-invariant, the MSNN can be used to create better generalization during face recognition. Feature extraction is performed on grayscale images using hit-miss transforms that are...


Platforms: Matlab

SINCO is a GPL library with functions to implement Artificial Neural Networks simulators. You are free to define the network (ilimited neurons and layers) and the functions (training, threshold, etc.).


Platforms: *nix

TDL - Win Neural Net Pattern Recog. Tool Quick, hassle-free automatic construction of NN by use of evolutionary processes. Trans-Dimensional Learning allows multiple data sets to be learned incrementally, regardless of differences in number of inputs and outputs. Complete graphical support of...


Platforms: Windows

annie stands for Artificial Neural Network Library and is a C++ API (library) for neural network training and execution. ersions exist for both Windows and flavours of Unix (tested on Linux). The library currently has support for training, saving and executing multi-layer perceptron,...


Platforms: *nix

AI::NNFlex is a base Perl class for implementing neural networks. SYNOPSIS use AI::NNFlex; my $network = AI::NNFlex->new(config parameter=>value); $network->add_layer( nodes=>x, activationfunction=>function); $network->init(); $network->lesion( nodes=>PROBABILITY,...


Platforms: *nix

The SigmaPi Neural Network Simulator is designed for time-series processing and neural network research on Unix/X11. Since version 0.5, it uses the LSTM neuron model, the RTRL training algorithm and a heuristic learning rate adaptation based on local update sign-changes. It is GPL-covered, so you...


Platforms: *nix

SNAKES is a Python library that provides all then necessary to define and execute many sorts of Petri nets, in particular those of the PBC and M-nets family. Its main aim is to be a general Petri net library, being able to cope with most Petri nets models, and providing the researcher with a tool...


Platforms: *nix

dANN library can help create artificial neural networks within other programs. It is currently written in Java, C++, and C#. However, C++ and C# versions can only be obtained through the SVN at the moment. Also, the C++ and C# versions are not properly documented and cleaned up, although they...


Platforms: *nix

AI::NeuralNet::BackProp is a simple back-prop neural net that uses Deltas and Hebbs rule. SYNOPSIS use AI::NeuralNet::BackProp; # Create a new network with 1 layer, 5 inputs, and 5 outputs. my $net = new AI::NeuralNet::BackProp(1,5,5); # Add a small amount of randomness to the network...


Platforms: *nix

KXNeur is a X Neural Switcher front-end for KDE. Its a program like Punto Switcher, but has other functionally and features. Last version can get from svn: svn://xneur.ru:3690/xneur/xneur and svn://xneur.ru:3690/xneur/kxneur PS XNeur homepage ( http://xneur.ru ) on Russian only PPS KXNeur...


Platforms: *nix

ffnet is meant to be an easy and fast feed-forward neural network training solution for python..


Platforms: *nix

scnANNlib is a Sentinel Chicken Networks Artificial Neural Network Library. Documentation on what is what can be found in README.files. Currently, the API specification and documentation can only be found in the source of the header files (in lib/), but this will be improved in later releases....


Platforms: *nix

Petri Net Editor is a small, easy to use, Java based application specially designed to offer users an editor for stochastic Petri-nets. This tool is designed to also allow you to create reachability trees and Markov graphs, simulate and gather statistics on simulation. for WindowsAll


Platforms: Windows

SPICE-MLP (the old name is SpiceNeuro or Neural Network Example - NNE) is a small application of Three-Layer Neural Network (NN) with multi-inputs and outputs, written for students who wanted to learn and develop their own NN applications. The purpose of this program is to get you started...


Platforms: Windows, Windows Vista, 7

The purpose of this program is to get you started quickly with Neural Network without having to go through lengthy theory of the Neural Network background. Once you understand these programs you will be able to consult the Neural Network materials on a need basis. Spice-SOM's arm is to introduce...


Platforms: Windows, Windows Vista, 7

GINNet, also known as the Graphical Interface for Neural Networks was developed as a decision-making platform written in Java. It has been designed in order to favorize the development and use of neural networks. It was create so that it could make, neural networks, teaching and evaluation easier.


Platforms: Windows

Multiple Back-Propagation is an easy to use application specially designed for the training of neural networks with the Back-Propagation and the Multiple Back-Propagation algorithms.


Platforms: Windows

AnimatLab is a simple, easy to use application specially designed to combine biomechanical simulation and biologically realistic neural networks. You can build the body of an animal, robot, or other machine and place it in a virtual world where the physics of its interaction with the...


Platforms: Windows