Home   >   CSC-OpenAccess Library   >    Manuscript Information
Full Text Available

(102.05KB)
This is an Open Access publication published under CSC-OpenAccess Policy.
Incorporating Kalman Filter in the Optimization of Quantum Neural Network Parameters
Hayder Mahdi Abdulridha
Pages - 28 - 38     |    Revised - 15-03-2012     |    Published - 16-04-2012
Volume - 3   Issue - 2    |    Publication Date - April 2012  Table of Contents
MORE INFORMATION
KEYWORDS
Quantum Neural Network, Extended Kalman filter, Training
ABSTRACT
Kalman filter have been used for the estimation of instantaneous states of linear dynamic systems. It is a good tool for inferring of missing information from noisy measurement. The quantum neural network is another approach to the merging of fuzzy logic with the neural network and that by the investment of quantum mechanics theory in building the structure of neural network. The gradient descent algorithm has been used, widely, in training the neural network, but the problem of local minima is one of the disadvantages of this algorithm. This paper presents an algorithm to train the quantum neural network by using the extended kalman filter.
CITED BY (0)  
1 Google Scholar
2 CiteSeerX
3 refSeek
4 Scribd
5 slideshare
6 PdfSR
1 R. Savitha, S. Suresh, and N. Surndararajan, "A Fast Learning Complex-valued Classifier for real-valued classification problems", IEEE International Conference on Neural Networks,2011, pp. 2243-2249.
2 G. Dahi, D. Yu, L. Deng, A. Acero, "Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition", IEEE Transaction on Audio speech and language, vol. 20, pp. 30-41, 2011.
3 M, Hou, X. Han, "Constructive Approximation to Multivariate Function by Decay RBF Neural Network", IEEE Transaction on Neural Networks, vol. 21, pp. 1517-1523, 2010.
4 C.E. Castaneda, A.G. Loukianov, E.N. Sanchez,. B. Castillo-Toledo, "Discrete Time Neural Sliding Block Control for a DC Motor With Controlled Flux", IEEE Transaction on Industrial Electronics, vol. 59, pp. 1194-1207, 2011.
5 R. Shi, J. Shi, Y. Guo, X. Peno, "Quantum MIMO Communication Scheme Based on Quantum Teleportation with Triplet State", International Journal of Theoretical Physics, vol.50, pp. 2334-2346, 2011.
6 Z. Chen, D. Dong, C. Zhang, "Quantum Control Based on Quantum Information", IEEE Chinese Control Conference, 2006, pp. 2121-2126.
7 B. Liu, F. Gao, Q. Wen, "Single-Photon Multiparty Quantum Cryptographic Protocols with Collective Detection", IEEE Journal of Quantum Electronics, vol. 47, pp. 1383-1390, 2011.
8 S. S. Stevens, C. T. Morgan and J. Volkmann, "Theory of the Neural Quantum in the Discrimination of Loudness and Pitch", The American Journal of Psychology, vol. 54, pp. 315-335, 1941.
9 G. Puruthaman, N.B. Karyiannis, "Quantum neural networks (QNNs): Inherently fuzzy feedforward neural networks", IEEE International Conference on Neural Networks, 1996, pp.1085-1090,.
10 H. Xiao, M. Cao, "Hybrid Quantum Neural Networks Model Algorithm and Simulation", IEEE International Conference on Natural Computation, 2009, pp. 164-168.
11 R. Mahjan, "Hybrid quantum inspired neural model fo commodity price prediction", IEEE International Conference on Advanced Communication Technology, 2011, pp. 1353-1357.
12 M. Brady, R. Raghavan, J. Slawny, "Gradient descent fails to separate", IEEE International Conference on Neural Networks, 1988, pp. 649-656.
13 A. Mohammad, F. Almasgani, N. Sadrieh, A. Zandi, "Incomplete spectrogram reconstruction kalman filter for noise robust speech recognition", IEEE International Symposium on Communucations, control and Signal Processing, 2008, pp. 814-818.
14 I. Arroca, R. Sanchis, "Adaptive extended Kalman filter for recursive identification under missing data", IEEE Conference on Decision and Control, 2010, pp. 1165-1170.
15 W. Yu, J. Rubio, X. Li, "Recurrent neural networks training with stable risk-sensitive Kalman filter algorithm", IEEE Internaional Joint Conference on Neural Networks, 2005, pp. 700-705.
16 R. Linsker, "Neural learning of Kalman filtering, Kalman control, and system identification",IEEE International Conference on Neural Networks, 2009, pp. 1835-1842.
17 X. Wang, Y. Huang, "Convergence Study in Extended Kalman Filter-Based Training of Recurrent Neural Networks", IEEE Transaction on Neural Networks, vol. 22, pp. 488-600,2011.
18 R. Zhou, Q. Ding, "Quantum M-P Neural Network", International Journal of Theoretical Physics, Springer, vol. 46, pp. 3209-3215, 2007.
19 R. Xianwem, Z. Feng, Z. Lingfeng, M. Xianwen, "Application of Quantum Neural Network Based on Rough Set in Transformer Fault Diagnosis", IEEE Asia-Pacific Power and Energy Engineering Conference, 2010, pp. 1-4.
20 J.L. Mitrpanont, A. Srisuphab, "The realization of quantum complex-valued backpropagation neural network in pattern recognition problem", IEEE International Conference on Neural Information Processing, 2002, pp. 462-466.
Dr. Hayder Mahdi Abdulridha
Babylon University - Iraq
drenghaider@yahoo.com