{"title":"Fast Complex Valued Time Delay Neural Networks","authors":"Hazem M. El-Bakry, Qiangfu Zhao","volume":17,"journal":"International Journal of Computer and Information Engineering","pagesStart":1640,"pagesEnd":1651,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/3218","abstract":"Here, a new idea to speed up the operation of\ncomplex valued time delay neural networks is presented. The whole\ndata are collected together in a long vector and then tested as a one\ninput pattern. The proposed fast complex valued time delay neural\nnetworks uses cross correlation in the frequency domain between the\ntested data and the input weights of neural networks. It is proved\nmathematically that the number of computation steps required for\nthe presented fast complex valued time delay neural networks is less\nthan that needed by classical time delay neural networks. Simulation\nresults using MATLAB confirm the theoretical computations.","references":"[1] H. M. El-Bakry, and Q. Zhao, \"Fast Pattern Detection Using Neural\nNetworks Realized in Frequency Domain,\" Proc. of the International\nConference on Pattern Recognition and Computer Vision, The Second\nWorld Enformatika Congress WEC'05, Istanbul, Turkey, 25-27 Feb.,\n2005.\n[2] H. M. El-Bakry, and Q. Zhao, \"Sub-Image Detection Using Fast Neural\nProcessors and Image Decomposition,\" Proc. of the International\nConference on Pattern Recognition and Computer Vision, The Second\nWorld Enformatika Congress WEC'05, Istanbul, Turkey, 25-27 Feb.,\n2005.\n[3] H. M. El-Bakry, and Q. Zhao, \"Fast Pattern Detection Using Normalized\nNeural Networks and Cross Correlation in the Frequency Domain,\"\naccepted and under publication in the EURASIP Journal on Applied\nSignal Processing.\n[4] H. M. El-Bakry, and H. Stoyan, \"Fast Neural Networks for Code\nDetection in a Stream of Sequential Data,\" Proc. of the International\nConference on Communications in Computing (CIC 2004), Las Vegas,\nNevada, USA, 21-24 June, 2004.\n[5] H. M. El-Bakry, \"Fast Neural Networks for Object\/Face Detection,\"\nProc. of 5th International Symposium on Soft Computing for Industry\nwith Applications of Financial Engineering, June 28 - July 4, 2004,\nSevilla, Andalucia, Spain.\n[6] A. Hirose, \"Complex-Valued Neural Networks\nTheories and Applications\", Series on innovative Intellegence, vol.5.\nNov. 2003.\n[7] H. M. El-Bakry, \"Face detection using fast neural networks and image\ndecomposition,\" Neurocomputing Journal, vol. 48, 2002, pp. 1039-\n1046.\n[8] H. M. El-Bakry, \"Human Iris Detection Using Fast Cooperative\nModular Neural Nets and Image Decomposition,\" Machine Graphics &\nVision Journal (MG&V), vol. 11, no. 4, 2002, pp. 498-512.\n[9] H. M. El-Bakry, \"Automatic Human Face Recognition Using Modular\nNeural Networks,\" Machine Graphics & Vision Journal (MG&V), vol.\n10, no. 1, 2001, pp. 47-73.\n[10] S. Jankowski, A. Lozowski, M. Zurada, \" Complex Valued Multistate\nNeural Associative Memory,\" IEEE Trans. on Neural Networks, vol.7,\n1996, pp.1491-1496.\n[11] H. M. El-Bakry, and Q. Zhao, \" New Fast Time Delay Neural\nNetworks,\" Accepted for publication in the International Conference on\nInformation and Knowledge Engineering (IKE'05), June 20-23, 2005,\nLas Vegas, USA.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 17, 2008"}