Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 2

matrix perturbation Related Publications

2 Principle Components Updates via Matrix Perturbations

Authors: Aiman Elragig, Hanan Dreiwi, Dung Ly, Idriss Elmabrook

Abstract:

This paper highlights a new approach to look at online principle components analysis (OPCA). Given a data matrix X R,^m x n we characterise the online updates of its covariance as a matrix perturbation problem. Up to the principle components, it turns out that online updates of the batch PCA can be captured by symmetric matrix perturbation of the batch covariance matrix. We have shown that as n→ n0 >> 1, the batch covariance and its update become almost similar. Finally, utilize our new setup of online updates to find a bound on the angle distance of the principle components of X and its update.

Keywords: covariance matrix, online data updates, matrix perturbation, online principle component analysis (OPCA)

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 481
1 A Comparison of First and Second Order Training Algorithms for Artificial Neural Networks

Authors: C. Ardil, Syed Muhammad Aqil Burney, Tahseen Ahmed Jilani

Abstract:

Minimization methods for training feed-forward networks with Backpropagation are compared. Feedforward network training is a special case of functional minimization, where no explicit model of the data is assumed. Therefore due to the high dimensionality of the data, linearization of the training problem through use of orthogonal basis functions is not desirable. The focus is functional minimization on any basis. A number of methods based on local gradient and Hessian matrices are discussed. Modifications of many methods of first and second order training methods are considered. Using share rates data, experimentally it is proved that Conjugate gradient and Quasi Newton?s methods outperformed the Gradient Descent methods. In case of the Levenberg-Marquardt algorithm is of special interest in financial forecasting.

Keywords: backpropagation algorithm, line search, matrix perturbation, conjugacy condition

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3245