The causes for premature saturation with backpropagation training

PDF Version Also Available for Download.

Description

The mechanism that causes the output nodes of feedforward multilayer networks mapped with sigmoid functions to prematurely saturate during backpropagation training are described. The necessary conditions for the occurrence of this undesirable phenomenon are also presented. Simulation results demonstrate the adequacy of the presented necessary conditions.

Physical Description

6 p.

Creation Information

Vitela, J. E. & Reifman, J. June 1, 1994.

Context

This article is part of the collection entitled: Office of Scientific & Technical Information Technical Reports and was provided by the UNT Libraries Government Documents Department to the UNT Digital Library, a digital repository hosted by the UNT Libraries. More information about this article can be viewed below.

Who

People and organizations associated with either the creation of this article or its content.

Authors

  • Vitela, J. E. Universidad Nacional Autonoma de Mexico, Mexico City (Mexico). Instituto de Ciencias Nucleares
  • Reifman, J. Argonne National Lab., IL (United States)

Sponsor

Publisher

Provided By

UNT Libraries Government Documents Department

Serving as both a federal and a state depository library, the UNT Libraries Government Documents Department maintains millions of items in a variety of formats. The department is a member of the FDLP Content Partnerships Program and an Affiliated Archive of the National Archives.

Contact Us

What

Descriptive information to help identify this article. Follow the links below to find similar items on the Digital Library.

Description

The mechanism that causes the output nodes of feedforward multilayer networks mapped with sigmoid functions to prematurely saturate during backpropagation training are described. The necessary conditions for the occurrence of this undesirable phenomenon are also presented. Simulation results demonstrate the adequacy of the presented necessary conditions.

Physical Description

6 p.

Notes

OSTI as DE94012464; Paper copy available at OSTI: phone, 865-576-8401, or email, reports@adonis.osti.gov

Source

  • Institute of Electrical and Electronic Engineers (IEEE) world congress on computational intelligence,Lake Buena Vista, FL (United States),28 Jun - 2 Jul 1994

Language

Item Type

Identifier

Unique identifying numbers for this article in the Digital Library or other systems.

  • Other: DE94012464
  • Report No.: ANL/RA/CP--81611
  • Report No.: CONF-940699--3
  • Grant Number: W-31109-ENG-38
  • Office of Scientific & Technical Information Report Number: 10153728
  • Archival Resource Key: ark:/67531/metadc1312638

Collections

This article is part of the following collection of related materials.

Office of Scientific & Technical Information Technical Reports

Reports, articles and other documents harvested from the Office of Scientific and Technical Information.

Office of Scientific and Technical Information (OSTI) is the Department of Energy (DOE) office that collects, preserves, and disseminates DOE-sponsored research and development (R&D) results that are the outcomes of R&D projects or other funded activities at DOE labs and facilities nationwide and grantees at universities and other institutions.

What responsibilities do I have when using this article?

When

Dates and time periods associated with this article.

Creation Date

  • June 1, 1994

Added to The UNT Digital Library

  • Nov. 3, 2018, 11:47 a.m.

Description Last Updated

  • Nov. 6, 2018, 7:11 p.m.

Usage Statistics

When was this article last used?

Yesterday: 0
Past 30 days: 0
Total Uses: 7

Interact With This Article

Here are some suggestions for what to do next.

Start Reading

PDF Version Also Available for Download.

International Image Interoperability Framework

IIF Logo

We support the IIIF Presentation API

Vitela, J. E. & Reifman, J. The causes for premature saturation with backpropagation training, article, June 1, 1994; Illinois. (https://digital.library.unt.edu/ark:/67531/metadc1312638/: accessed April 24, 2024), University of North Texas Libraries, UNT Digital Library, https://digital.library.unt.edu; crediting UNT Libraries Government Documents Department.

Back to Top of Screen