Phys. Rev. Lett. 79, 2578–2581 (1997)Globally Optimal Parameters for On-Line Learning in Multilayer Neural NetworksReceived 14 February 1997; published in the issue dated 29 September 1997 We present a framework for calculating globally optimal parameters, within a given time frame, for on-line learning in multilayer neural networks. We demonstrate the capability of this method by computing optimal learning rates in typical learning scenarios. A similar treatment allows one to determine the relevance of related training algorithms based on modifications to the basic gradient descent rule as well as to compare different training methods. © 1997 The American Physical Society URL:
http://link.aps.org/doi/10.1103/PhysRevLett.79.2578
DOI:
10.1103/PhysRevLett.79.2578
PACS:
87.10.+e, 02.50.-r, 05.20.-y
|
|
About | Terms and Conditions | Subscriptions | Search | Help
Use of the American Physical Society websites and journals implies that the user has read and agrees to our Terms and Conditions and any applicable Subscription Agreement. Physical Review®, Physical Review Letters®, Reviews of Modern Physics®, and Physical Review Special Topics® are trademarks of the American Physical Society.