backpropagation

From Glossary of Meteorology
The most common method of training an artificial neural network.

A training set, consisting of examples of input data for which the output is known, is presented to the network, and the network weights are adjusted until the network produces results that are in agreement with the training set. This type of network is often used in prediction and in classification.

Copyright 2024 American Meteorological Society (AMS). For permission to reuse any portion of this work, please contact permissions@ametsoc.org. Any use of material in this work that is determined to be “fair use” under Section 107 of the U.S. Copyright Act (17 U.S. Code § 107) or that satisfies the conditions specified in Section 108 of the U.S.Copyright Act (17 USC § 108) does not require AMS’s permission. Republication, systematic reproduction, posting in electronic form, such as on a website or in a searchable database, or other uses of this material, except as exempted by the above statement, require written permission or a license from AMS. Additional details are provided in the AMS Copyright Policy statement.