Soft de IA para clasificación y regresión de datos

Nuclass7 y Numap7 son dos aplicaciones de los Laboratorios Neural Decision que poseen una versión freeware (con restricciones de tamaño del modelo): Nuclass7 es para trabajar en clasificación (es posible usar redes neuronales) y Numap7 es para análisis de regresión y asociación. Pienso que pueden ser útiles para estudiantes de asignaturas de minería de datos, inteligencia artificial en grado y postgrado.

Nuclass7 7.06a : 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.

Numap7: Freeware for fast training, validation, and application of regression/approximation networks including the multilayer perceptron (MLP), functional link network, and piecewise linear network. The self organizing map (SOM) and K-Means clustering are also included. Fast pruning algorithms create and validate 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 training error and cluster formation are included. Extensive help files are provided in the software. Numap7 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 Numap7 limits the MLP to 10 hidden units and limits the PLN to 10 clusters. Upgradable to commercial versions which lack these limitations. The classification (decision making) version of this software, called Nuclass7, is also available. Numap7.0 was developed by the Image Processing and Neural Networks Lab of Univ. of Texas at Arlington, and by Neural Decision Lab LLC.