A new fast neural network model

  • Authors:
  • Hazem M. El-Bakry;Nikos Mastorakis

  • Affiliations:
  • Faculty of Computer Science & Information Systems, Mansoura University, Egypt;Technical University of Sofia, Bulgaria

  • Venue:
  • ACACOS'12 Proceedings of the 11th WSEAS international conference on Applied Computer and Applied Computational Science
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, a new model for testing patterns with neural networks is presented. The idea is to accelerate the operation of testing patterns by using neural networks. This is done by applying cross correlation between the input patterns and the input weights of neural networks in the frequency domain rather than time domain. Furthermore, such model is very useful for understanding the internal relation between the tested patterns. In addition, the input patterns are collected in one vector and manipulated as a one pattern. Then, the important data (code) can be hidden and encrypted inside the whole input data and this is very useful for security applications. Moreover, it can be applied successfully for pattern/data analysis application. Simulation results confirm the theoretical considerations..