Recent developments of the SNNS neural network simulator

摘要

A neural network simulator for Unix workstations, SNNS, under development at the Universitat Stuttgart, Germany, is described. The network simulation environment is a tool to generate, train, test, and visualize artificial neural networks. The simulator consists of three major components: a simulator kernel that operates on the internal representation of the neural networks, a graphical user interface based on X-Windows to interactively construct and change small neural nets, and a compiler to generate the internal representation of large neural networks from a high-level network description language.