Prediction capability of neural networks trained by Monte-Carlo paradigm

Ray R. Hashemi, Aslam H. Chowdhury, Nancy L. Stafford, John R. Talburt

Research output: Contribution to book or proceedingConference articlepeer-review

2 Scopus citations

Abstract

The Monte-Carlo training paradigm for Artificial Neural Networks has been studied, the training short cut to reduce the training time has been discussed, and the prediction capability of such a trained neural network has been compared with the prediction capability of a neural net trained by the Backpropagation paradigm and with the statistical approach of the Discriminant Analysis. The Artificial Neural Network trained by the Monte-Carlo method proves itself as a reliable prediction tool which is superior to Discriminant Analysis and the Backpropagation training paradigm.

Original languageEnglish
Title of host publicationProceedings of the 1993 ACM/SIGAPP Symposium on Applied Computing
Subtitle of host publicationStates of the Art and Practice, SAC 1993
EditorsEd Deaton, George Hedrick, K.M. George, Hal Berghel
PublisherAssociation for Computing Machinery
Pages9-13
Number of pages5
ISBN (Electronic)0897915674
DOIs
StatePublished - Mar 1 1993
Event1993 ACM/SIGAPP Symposium on Applied Computing: States of the Art and Practice, SAC 1993 - Indianapolis, United States
Duration: Feb 14 1993Feb 16 1993

Publication series

NameProceedings of the ACM Symposium on Applied Computing
VolumePart F129680

Conference

Conference1993 ACM/SIGAPP Symposium on Applied Computing: States of the Art and Practice, SAC 1993
Country/TerritoryUnited States
CityIndianapolis
Period02/14/9302/16/93

Scopus Subject Areas

  • Software

Keywords

  • Intelligent systems
  • Machine learning
  • Neural netwok

Fingerprint

Dive into the research topics of 'Prediction capability of neural networks trained by Monte-Carlo paradigm'. Together they form a unique fingerprint.

Cite this