论文信息 - A Robust Subspace Algorithm for Principal Component Analysis

A Robust Subspace Algorithm for Principal Component Analysis

We present a noise robust PCA algorithm which is an extension of the Oja subspace algorithm and allows tuning the noise sensitivity. We derive a loss function which is minimized by this algorithm and interpret it in a noisy PCA setting. Results on the local stability analysis of this algorithm are given and it is shown that the locally stable equilibria are those which minimize the loss function.

Kurt Hornik | Andreas Weingessel

[1] Kurt Hornik,et al. Learning in linear neural networks: a survey , 1995, IEEE Trans. Neural Networks.

[2] Michael G. Strintzis,et al. Optimal linear compression under unreliable representation and robust PCA neural models , 1999, IEEE Trans. Neural Networks.

[3] K. I. Diamantaras. Robust principal component extracting neural networks , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[4] E. Oja. Simplified neuron model as a principal component analyzer , 1982, Journal of mathematical biology.

[5] Erkki Oja,et al. Neural Networks, Principal Components, and Subspaces , 1989, Int. J. Neural Syst..

[6] Alan L. Yuille,et al. Robust principal component analysis by self-organizing rules based on statistical physics approach , 1995, IEEE Trans. Neural Networks.

[7] Kurt Hornik,et al. Convergence analysis of local feature extraction algorithms , 1992, Neural Networks.

[8] Harold J. Kushner,et al. wchastic. approximation methods for constrained and unconstrained systems , 1978 .

[9] Lei Xu,et al. Self-Organizing Rules for Robust Principal Component Analysis , 1992, NIPS.