NNN is a general pupose neural network modelling tool with the Pascal code generator. There are three versions of NNN - for DOS, for Windows and a Web-based version (runs on Windows-based computers across the Web).

NNN allows creation of artificial neural networks (ANNs) with one hidden layer. Two types of networks, namely Error Backpropagation and Radial Basis Function networks are supported in this version. In the case of Error Backpropagation Network all neurons are of sigmoid-type, and the direct input-output link can be made as well. In the Radial Basis Network the mapping function is of Gaussian type for the hiden layer and linear for the output layer.

Try running WebNNN right in your browser over Internet
(in Internet Explorer)

Brief NNN user's guide

NNN screen dump (35K)

More on neural networks