A New Fast Forecasting Technique using High Speed Neural Networks

  title={A New Fast Forecasting Technique using High Speed Neural Networks},
  author={Hazem M. El-Bakry},
Forecasting is an important issue for many different applications. In this paper, a new efficient forecasting technique is presented. Such technique is designed by using fast neural networks (FNNs). The new idea relies on performing cross correlation in the frequency domain between the input data and the input weights of neural networks. It is proved mathematically and practically that the number of computation steps required for the proposed fast forecasting technique is less than that needed… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 54 references

New High Speed Normalized Neural Networks for Fast Pattern Discovery on Web Pages

  • H. M. El-Bakry
  • the International Journal of Computer Science and…
  • 2006
Highly Influential
4 Excerpts

Speeding-up Normalized Neural Networks For Face/Object Detection

  • H. M. El-Bakry, Q. Zhao
  • Machine Graphics & Vision Journal (MG&V), vol. 14…
  • 2005
Highly Influential
4 Excerpts

FNNs for Code Detection in Sequential Data Using Neural Networks for Communication Applications

  • H. M. El-Bakry, H. Stoyan
  • Proc. of the First International Conference on…
  • 2004
Highly Influential
4 Excerpts

Automatic Human Face Recognition Using Modular Neural Networks

  • H. M. El-Bakry
  • Machine Graphics & Vision Journal (MG&V), vol. 10…
  • 2001
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…