This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
An Adaptive Stochastic Approximation Algorithm for Simultaneous Diagonalization of Matrix Sequences With Applications
March 1997 (vol. 19 no. 3)
pp. 282-287

Abstract—We describe an adaptive algorithm based on stochastic approximation theory for the simultaneous diagonalization of the expectations of two random matrix sequences. Although there are several conventional approaches to solving this problem, there are many applications in pattern analysis and signal detection that require an online (i.e., real-time) procedure for this computation. In these applications, we are given two sequences of random matrices {Ak} and {Bk} as online observations, with limk→∞ E[Ak] = A and limk→∞ E[Bk] = B, where A and B are real, symmetric and positive definite. For every sample (Ak,Bk), we need the current estimates Φk and Λk respectively of the eigenvectors Φ and eigenvalues Λ of A−1B. We have described such an algorithm where Φk and Λk converge provably with probability one to Φ and Λ respectively. A novel computational procedure used in the algorithm is the adaptive computation of A−½. Besides its use in the generalized eigen-decomposition problem, this procedure can be used on its own in several feature extraction problems. The performance of the algorithm is demonstrated with an example of detecting a high-dimensional signal in the presence of interference and noise, in a digital mobile communications problem. Experiments comparing computational complexity and performance demonstrate the effectiveness of the algorithm in this real-time application.

[1] P.F. Baldi and K. Hornik, "Learning in Linear Neural Networks: A Survey," IEEE Trans. Neural Networks, vol. 6, no. 4, pp. 837-858, 1995.
[2] C. Chatterjee, "Adaptive Self-Organizing Neural Networks for Matrix Eigen-Decomposition Problems and their Applications to Feature Extraction," PhD dissertation, Purdue Univ., School of Electrical Engineering, West Lafayette, Ind., May 1996.
[3] K. Fukunaga, Introduction to Statistical Pattern Recognition, Second ed. New York: Academic Press, 1990.
[4] G.H. Golub and C.F. VanLoan, Matrix Computations.Baltimore, Md.: Johns Hopkins Univ. Press, 1983.
[5] L. Ljung, "Analysis of Recursive Stochastic Algorithms," IEEE Trans. Automatic Control, vol. 22, no. 4, pp. 551-575, 1977.
[6] J.C. Mao and A.K. Jain, “Artificial Neural Networks for Feature Extraction and Multivariate Data Projection,” IEEE Trans. Neural Networks, vol. 6, no. 2, pp. 296-317, 1995.
[7] T.D. Sanger, "Optimal Unsupervised Learning in a Single-Layer Linear Feedforward Neural Network," Neural Networks, vol. 2, pp. 459-473, 1989.
[8] M.D. Zoltowski, J. Ramos, C. Chatterjee, and V.P. Roychowdhury, "Blind Adaptive 2D RAKE Receiver for DS-CDMA Based on Space-Frequency MVDR Processing," unpublished paper.

Index Terms:
Adaptive generalized eigen-decomposition, interference cancellation.
Citation:
Chanchal Chatterjee, Vwani P. Roychowdhury, "An Adaptive Stochastic Approximation Algorithm for Simultaneous Diagonalization of Matrix Sequences With Applications," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 3, pp. 282-287, March 1997, doi:10.1109/34.584108
Usage of this product signifies your acceptance of the Terms of Use.