3
Views
0
CrossRef citations to date
0
Altmetric
Original Article

Macroscopic properties of the cost function of a feed-forward neural network prior to training

Pages 389-400 | Received 08 Feb 1994, Published online: 09 Jul 2009
 

Abstract

By making simple assumptions regarding the nodal potentials we have been able to obtain analytic expressions for the mean and standard deviation of the cost-function values of a feed-forward multilayer network, with continuous activation units, prior to training. We have also obtained means of the derivatives, with respect to the weights and biases, of the cost function. The expressions have been used to obtain systematic estimates of the learning rate required for backpropagation training. The results are exemplified using an 8-3-8 encoder network.

Reprints and Corporate Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

To request a reprint or corporate permissions for this article, please click on the relevant link below:

Academic Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

Obtain permissions instantly via Rightslink by clicking on the button below:

If you are unable to obtain permissions via Rightslink, please complete and submit this Permissions form. For more information, please visit our Permissions help page.