Freeware for fast training, validation, and application of classification type networks including the multilayer perceptron (MLP), functional link network, piecewise linear network, and nearest neighbor classifier. The self organizing map (SOM) and K-Means clustering are also included. Fast pruning algorithms create a nested sequence of different size networks, to facilitate structural risk minimization. C source code for applying trained networks is provided, so users can use networks in their own applications. User-supplied txt-format training data files, containing rows of numbers, can be of any size. Example training data is also provided. Fast VB Graphics for network classification error and SOM cluster formation are included. Extensive help files are provided in the software.
Nuclass7 is highly automated and requires very few parameter choices by the user. This version runs significantly faster. Advanced features include network sizing and feature selection. Training data can be compressed using the discrete Karhunen-Loeve' transform (KLT). This Basic version of Nuclass7 limits the MLP to 10 hidden units, the PLN to 10 clusters, and the NNC to 50 clusters. Upgradable to the commercial version, which lacks these limitations. The regression/approximation version of this software, called Numap7, is also available. Nuclass7 was developed by the Image Processing and Neural Networks Lab of Univ. of Texas at Arlington, and by Neural Decision Lab LLC.
Nuclass7 Freeware for fast training, validation, and application of neural and conventional classifiers including MLP, functional link net, piecewise linear net, nearest neighbor classifier, self organizing map. Extensive help. C source for trained nets
MLP-Class Source code for fast training of multilayer perceptron classifier. Data files included. Source code for applying the trained network. Resulting networks can be pruned by NuClass7.06. For winzip password: http://www-ee.uta.edu/eeweb/ip/Software.htm.
MLP-Map Source code for training of multilayer perceptron for approximation. Data files included. Source code for applying the trained network. Resulting networks can be pruned by NuMap7.06. For winzip password: http://www-ee.uta.edu/eeweb/ip/Software.htm.
Numap7 Freeware for fast development and application of regression type networks including the multilayer perceptron, functional link net, piecewise linear network, self organizing map and K-Means. Extensive help. C source code for applying trained nets.
Numap7 Freeware for fast development and application of regression type networks including the multilayer perceptron, functional link net, piecewise linear network, self organizing map and K-Means. Extensive help. C source code for applying trained nets.
LTF-Cimulator LTF-Cimulator is software for easy simulation and development of LTF-C neural networks. You can train and test a network, save it in a readable text format or perform cross-validation. Training parameters can be chosen automatically by LTF-Cimulator.
EasyNN-plus EasyNN-plus 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 and images.
EasyNN 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.
NeuroSolutions NeuroSolutions is a highly graphical neural network development tool for Windows. It is a virtually unconstrained environment for designing neural networks for research or to solve real-world problems.
NeuroSolutions for MATLAB The NeuroSolutions for MATLAB neural network toolbox is a valuable addition to MATLAB's technical computing capabilities allowing users to leverage the power of NeuroSolutions (www.neurosolutions.com) inside MATLAB and Simulink.
NeuroDiet NeuroDiet is a neural network application that learns how the foods you eat are related to your health and fitness. All the neural network functions are managed automatically. You don't need to know anything about neural networks.
