neural network

From Glossary of Meteorology
Usually used to mean "artificial neural network," a computer program inspired by simple models of the brain.

It consists of a network of nodes connected by weighted links that establish the relationships between nodes. Each node sums the weighted inputs entering it and compares the result to a (usually) nonlinear function to produce its own output. Most neural networks have a training rule establishing how the weights are adjusted to bring the average output closest to that desired. The term can also mean the computer chip containing the fully trained (unmodifiable) system used in automatic sensors and controls.
See also machine learning.

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.