Overview

back propagation


Show Summary Details

Quick Reference

A supervised learning procedure for training feed-forward neural networks to learn from test samples. A series of test cases, known as the training set, are presented to the net, one at a time. The errors between the actual and desired output of the net are propagated backward to the internal layer(s) in order to adjust the connection weights in proportion to their contribution to the error. The least mean squares of the errors is often used as the optimizing criterion.

Subjects: Computing.


Reference entries

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.