Single Layer

See a layer of two neurons trying to learn AND and OR or two data problems. Two of these work!

You can set the learning rate and momentum.

Test Net applies the next line from the training set. The inputs, target, output and Delta values are shown.

Teach Net applies the data and adjust the weights.

Auto repeatedly applies the data, adjusting the weights. Learning stops when you press STOP or the epochs taken exceeds the maximum specified OR SSE < specified amount. If you then press Auto Teach again, learning will resume.

When learning stops the variation of SSE vs Epoch is plotted, and the feature space for each target is shown, together with the line associated with the weights of the associated neuron.

Reset reinitialises the weights

Go Back