See a simple MLP learning a non linear problem.
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. When you press Stop the learning stops and the variation of SSE vs Epoch is plotted. If you then press Auto Teach again, learning will resume.
Teaching will also stop when the epochs taken exceeds the maximum specified or the SSE is less than the specified value.
Reset reinitialises the weights
Learning rate Momentum
Stop learning after Epochs OR when SSE < .