Prediction of Neural Net Tolerance to Noise

  • Authors:
  • Khalid A. Al-Mashouq

  • Affiliations:
  • EE Department, King Saud University, Riyadh 11421, Saudi Arabia E-mail: mashouq@ix.netcom.com

  • Venue:
  • Neural Processing Letters
  • Year:
  • 1997

Quantified Score

Hi-index 0.00

Visualization

Abstract

To protect a feed-forward neural net against errors,error correcting codes have been used in previous studiesto encode the output label.Here we analyze the effect of additive noise onthe performance of a 1-layer coded net and compare it to an uncoded net.The derived results are then usedto predict the performance of any multilayer neural net.