Simulates MLP, RMLP and Cascade-Correlation models with dynamic size adjustment algorithms. Includes various training patterns, error and activation functions.

Class framework to create neural networks with arbitrary topology and mixed type of neurons, developed for research purpose. Includes technical information and discussion mailing-list.

A neural network based system to recognize leaves written in Java. A Java-Applet is also available.

An environment for neural network research, design, and simulation within MATLAB.

Neural network simulators for eight different network architectures with embedded example applications coded in portable ANSI C.

Professional II/PLUS is a neural network development environment. Available for Windows and Unix. Predict is a neural network tool for solving prediction and classification problems. Available for Unix or as an Excel add-in for Windows.

An opensource .NET OOP library project written in C# to generate, propagate and train complex neural feedforward networks.

Model Manager for development of bayesian neural networks.

Neural network COM+ components and development environment for forecasting and data analysis. Supports several algorithms. Trial version is available.

Showcases a java applet demo of a trained neural network piloting a lunar-lander type spacecraft over landscapes of various complexity.