Neural Network Excel

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

StrBio is a set of Java classes and libraries useful for development of software for computational structural biology research. They are licenced under the LGPL. he strbio.org classes are the basis for several published research projects, including the Pred2ary secondary structure prediction... Platforms: *nix

OpenDiscreteDynamicProgrammingTemplate project founds optimal constrainted parameters of a discrete controls with second order optimization template replacing Hessian with directional derivatives and backpropagation for digital filter(as neural network).. OpenDiscreteDynamicProgrammingTemplate:... 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

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

Uncle Unc is an application that provides an integrated view of structured data sources. Using a very flexible and powerful representation model, many services can be represented in Uncle Unc. Uncle Unc is a framework for network data-sharing, enabling remote administration and access to a... Platforms: *nix

KMemAid is like a traditional flash-card program to help you memorise question/answer pairs, but with an important twist: it uses a neural network to schedule the best time for an item to come up for review. Difficult items that you tend to forget quickly will be scheduled more often, while... Platforms: *nix

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

Statistics::LTU is an implementation of Linear Threshold Units. SYNOPSIS use Statistics::LTU; my $acr_ltu = new Statistics::LTU::ACR(3, 1); # 3 attributes, scaled $ltu->train([1,3,2], $LTU_PLUS); $ltu->train([-1,3,0], $LTU_MINUS); ... print "LTU looks like this:n"; $ltu->print;... Platforms: *nix

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... Platforms: BSD Solaris

Tremani Neural Network allows you to build, train and employ neural networks in PHP. It is easy to use and set up, and does not rely on external software to be installed on your webserver. Above all, the software is open source, which means you can use and modify it freely.A neural network can be... Platforms: Windows, Mac, *nix, PHP, BSD Solaris

Neuroph OCR - Handwriting Recognition is developed to recognize hand written letter and characters. It's engine derived's from the Java Neural Network Framework - Neuroph and as such it can be used as a standalone project or a Neuroph plug in. Platforms: Windows, Mac, Linux

The SigmaPi Neural Network Simulator is designed for time-series processing and neural network research on Unix/X11. It uses the LSTM neuron model, the RTRL training algorithm and a heuristic learning rate adaptation based on local update sign-changes.To use SigmaPi, you should know how a... Platforms: Windows, Mac, *nix, C/C++, BSD Solaris

Linasf is a Spam filter developed completely on PHP. It’s power comes from it’s design, it comprises a Bayesian Filter for a first categorization of content as well as user defined rules, and finally it’s all weighted with an Artificial Neural Network. The power of this design (roughly the... Platforms: Windows, Mac, *nix, PHP, BSD Solaris

Simple tutorial on pattern recognition using back propagation neural networks. the program has 3 classes with 3 images per class. Platforms: Matlab

KnowledgeMiner (yX) for Excel Free – Entry-Level Knowledge and Data Mining for Everybody. Simple, objective, fast. Develop reliable predictive models in only two steps. You know about the value of your data? Find unknown relevant relationships in your scientific, business or personal data... Platforms: Mac

Neural network classification results live view (like a movie). Free software for playing with neural networks classification. Major features * Easy, ready to play with. * Live view. * Many network architectures. * Different shapes of training data sets. * Learning with backpropagation... Platforms: Windows

iSNS is an interactive neural network simulator written in Java/Java3D. The program is intended to be used in lessons of Neural Networks. The program was developed by students as the software project at Charles University in Prague. Platforms: Windows, Mac, Linux

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... Platforms: BSD Solaris

This demo gives a clear visual presentation of what happens during the Adaboost algorithms. It shows how the decision boundary, example weights, training error and base learner weights change during training.A selection of base learning algorithms are included: Linear Regression, Naive Bayes,... Platforms: Matlab