Backpropagation made a tremendous step forward from the *
single-layer perceptron* network. With a more sophisticated learning rule,
backpropagation networks overcome the limitations that single-layer
networks have. Backpropagation is also the most suitable learning
method for multilayer networks. Perhaps, the reason why the
backpropagation made the major turning point is because the learning rule
has a solid mathematical foundation and it is practical [Ler91].

- 2.4.1 Linear Separability and the XOR Problem
- 2.4.2 Architecture of Backpropagation Networks
- 2.4.3 Backpropagation Processing Unit
- 2.4.4 Backpropagation Learning Algorithm
- 2.4.5 Local Minimum Problem
- 2.4.6 Generalization