Fast Complex Valued Time Delay Neural Networks

Here, a new idea to speed up the operation of complex valued time delay neural networks is presented. The whole data are collected together in a long vector and then tested as a one input pattern. The proposed fast complex valued time delay neural networks uses cross correlation in the frequency domain between the tested data and the input weights of neural networks. It is proved mathematically that the number of computation steps required for the presented fast complex valued time delay neural networks is less than that needed by classical time delay neural networks. Simulation results using MATLAB confirm the theoretical computations.

Authors:

• Hazem M. El-Bakry
• Qiangfu Zhao

Keywords:

• Fast Complex Valued Time Delay Neural Networks
• Cross Correlation
• Frequency Domain

References:

[1] H. M. El-Bakry, and Q. Zhao, "Fast Pattern Detection Using Neural
Networks Realized in Frequency Domain," Proc. of the International
Conference on Pattern Recognition and Computer Vision, The Second
World Enformatika Congress WEC'05, Istanbul, Turkey, 25-27 Feb.,
2005.
[2] H. M. El-Bakry, and Q. Zhao, "Sub-Image Detection Using Fast Neural
Processors and Image Decomposition," Proc. of the International
Conference on Pattern Recognition and Computer Vision, The Second
World Enformatika Congress WEC'05, Istanbul, Turkey, 25-27 Feb.,
2005.
[3] H. M. El-Bakry, and Q. Zhao, "Fast Pattern Detection Using Normalized
Neural Networks and Cross Correlation in the Frequency Domain,"
accepted and under publication in the EURASIP Journal on Applied
Signal Processing.
[4] H. M. El-Bakry, and H. Stoyan, "Fast Neural Networks for Code
Detection in a Stream of Sequential Data," Proc. of the International
Conference on Communications in Computing (CIC 2004), Las Vegas,
Nevada, USA, 21-24 June, 2004.
[5] H. M. El-Bakry, "Fast Neural Networks for Object/Face Detection,"
Proc. of 5th International Symposium on Soft Computing for Industry
with Applications of Financial Engineering, June 28 - July 4, 2004,
Sevilla, Andalucia, Spain.
[6] A. Hirose, "Complex-Valued Neural Networks
Theories and Applications", Series on innovative Intellegence, vol.5.
Nov. 2003.
[7] H. M. El-Bakry, "Face detection using fast neural networks and image
decomposition," Neurocomputing Journal, vol. 48, 2002, pp. 1039-
1046.
[8] H. M. El-Bakry, "Human Iris Detection Using Fast Cooperative
Modular Neural Nets and Image Decomposition," Machine Graphics &
Vision Journal (MG&V), vol. 11, no. 4, 2002, pp. 498-512.
[9] H. M. El-Bakry, "Automatic Human Face Recognition Using Modular
Neural Networks," Machine Graphics & Vision Journal (MG&V), vol.
10, no. 1, 2001, pp. 47-73.
[10] S. Jankowski, A. Lozowski, M. Zurada, " Complex Valued Multistate
Neural Associative Memory," IEEE Trans. on Neural Networks, vol.7,
1996, pp.1491-1496.
[11] H. M. El-Bakry, and Q. Zhao, " New Fast Time Delay Neural
Networks," Accepted for publication in the International Conference on
Information and Knowledge Engineering (IKE'05), June 20-23, 2005,
Las Vegas, USA.