Lines
In this problem we have taught NeuroShell to recognize which of 5 line shapes have been entered into the 10 input neurons. This example uses a Backpropagation network.
Spirals
This example uses a PNN network from the Advanced System to determine which of two intersecting spirals a given point lies on.
Saddle
This problem is designed to demonstrate the capability of General Regression Neural Networks (GRNN). GRNN will be used to fit a surface through a number of points in 3 dimensional space. We will be modeling the Saddle function, z=x^2  y^2 (where x^2 means x squared). The Saddle function is so named because its graph looks like a saddle.
Realty
This example uses a Kohonen network from the Advanced System to classify houses with specified characteristics into low, medium, and high price categories based upon physical characteristics.
XOR
This is the famous Exclusive Or problem (XOR) which, though trivial, has long been a benchmark test for neural networks. The reason for this is that early neural networks (perceptrons) in the 1960s could not solve it. That deficiency in neural networks of the time lead researchers to concentrate Artificial Intelligence research into symbolic processing methods instead of neural networks. By the late 1980s, networks, especially multilayer feedforward Backpropagation networks could easily solve the problem.
