Deep Learning by Josh Patterson and Adam Gibson

Deep Learning by Josh Patterson and Adam Gibson

Author:Josh Patterson and Adam Gibson
Language: eng
Format: mobi
Publisher: O'Reilly Media, Inc.
Published: 2017-08-09T16:00:00+00:00


Good Initial Learning Rates

Ideally, we begin with a large learning rate, and if the learning process diverges, we divide this rate by a factor and try again until the learning process begins to converge.

We suggest starting out with the following learning rates and then see which is the most stable: [ 0.1, 0.01, 0.001 ], with 0.001 being one of the most popular places to begin.

We also suggest trying learning rate methods in the following order:

Adam Currently recommended as the default method to use



Download



Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.