Neural Network Car

This function constructs a bottleneck (or autoassociative) neural network. It is used for dimensionality reduction or nonlinear principle components analysis. This function was tested under MATLAB 5.3, and requires the Neural Network toolbox.

EasyNN is a neural network system for Microsoft Windows. It makes the creation of neural networks easy. It allows the user to produce multilayer neural networks from a grid or from text files. The user can produce training, validating and querying files using the facilities in EasyNN or using...

Psychonet is a  tool for analyzing data.  Simply put, it finds patterns based on previous history that has been stored in the network through a process known as training.  Once a Psychonet neural network has been trained it can quickly compute answers or predictions given a new set of current...


Platforms: Windows, Mac, *nix, Windows CE

Alyuda Forecaster XL is a forecasting tool for MS Excel based on neural networks. It is the first choice for Excel users who need a quick-to-learn and reliable forecasting tool embedded into familiar Excel interface. Forecaster XL is designed especially for easy and reliable forecasting, saving...


Platforms: Windows

The expected performance of a stock depends on quality of the company, market evaluation of its stock, and macroeconomic environment. Also general market current condition is a significant contributing factor in the stock performance. So that it is clear that a good investing decision should be...


Platforms: Windows

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

DynNet is built as a Java library that contains basic elements that are necessary in order to build neural networks. Neural network classical models are already available (Multi-layer perceptron, Kohonen self-organizing maps, neural gas, growing neural gas, etc.).


Platforms: Windows

Walnut is an OpenSource framework for the development of neural network simulations by both beginners and experts. It is a system that is extensible with new paradigms. Neural network architectures and simulations are portable between various platforms (notably Windows and Unix). These objectives...


Platforms: Windows

RNNLIB is a recurrent neural network library for sequence learning problems. Applicable to most types of spatiotemporal data, it has proven particularly effective for speech and handwriting recognition.


Platforms: *nix

FullRecall is a software that learns itself about your memory in order to help you memorize knowledge effectively by scheduling optimal intervals between repetitions. Uses artificial neural network, which gradually grasps your forgetting curve, to schedule reviews for a day when you'll be...


Platforms: Windows, *nix

RHiTech NeuronNet v 1.0b - this COM component allows emulating neural network and training it by the error back-propogation algorithm. Installation with example included.


Platforms: Windows

Stock Market Browser is the perfect tool for day trading and stock market analysis. This very small and quick stock market browser (written in machine language) packs a big punch with a latest videos link, live stock scan with neural network A.I. actually gives buy and sell triangle...


Platforms: Windows

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

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

HyperNext Studio comprises three complementary applications (Creator, Developer, Player) that help you create, develop and distribute your own software. Together they make up a powerful but easy to use software creation system that allows hobbyists, students, educators, developers, in fact...


Platforms: Mac

The system is intended for stock market traders and consists of 3 modules: TA-1, SMAP-3, and NNSTP-2. It is a comprehensive system with user-friendly interfaces that is easy to use. Technical Analyzer TA-1 is based on predictive models including technical analysis and pattern recognition....


Platforms: Windows

Simple program for artificial neural network users. Right now the program can manipulate with Feed forward back propagation network.


Platforms: Windows, Mac, Linux

A java based neural network framework. The Auratus network is built around an XML messaging system, allowing for a complete MVC design. Additionally, Auratus networks are constructed and at the node/edge level, allowing for advanced topologies.


Platforms: Windows, Mac, Linux

Cluster Networks are a new style of neural simulation / neural network modeling, that models networks of neural populations ('clusters') that transform and transmit information using precisely-timed, graded bursts ('pulses' or 'volleys') of firing.


Platforms: Windows, Mac, Linux