Backpropogation is a supervised learning for multi-level neural networks. For each training example, it takes the difference between the expected and actual output at the final layer and then uses the differential of the {sigmoid}} function at each node to work out error values at earlier layers and hence update the weights on links between nodes.
Defined on page 112
Used on pages 112, 114, 141, 150, 180, 181, 188, 497
Also known as backprop