Details

Autor(en) / Beteiligte

• Zhou, S.
• Popovic, D.
• Schulz-Ekloff, G.

Titel

An improved learning law for backpropagation networks

Ist Teil von

• IEEE International Conference on Neural Networks, 1993, p.573-579 vol.1

Ort / Verlag

IEEE

Erscheinungsjahr

1993

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• An updating law for the adaptive selection of the step size (or the learning rate) is introduced. It is especially suitable for pattern learning, and is based on a vectorial analysis to a modified backpropagation network with updatable nonlinearities of neurons. The application to a simulated data set is included to demonstrate the effectiveness of the proposed approach. Some comparisons of performances of networks, with and without updatable nonlinear elements, as well as between the conventional and the proposed updating law, are presented.< >