Laboratory of Computer and Information Science

Erkki Oja:

Older PCA / ICA papers available on-line

The first list below contains some of my older PCA papers which are often asked for, but may not be readily available. I have scanned them into pdf files. Clicking the paper name should bring the paper on your screen, from which you can print it. The second list contains some more recent stuff on nonlinear PCA and ICA.

NOTE: The manuscripts themselves may not contain proper bibliographic data (where and when they have been published). Should you wish to cite one of the papers, please use the information on the following list.

Papers on neural PCA and "Oja's rule": Oja, E.: A simplified neuron model as a principal component analyzer. J. Math. Biol. 15, pp. 267-273 (1982).; Oja, E. and Karhunen, J.: On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix. J. Math. Anal. Appl 106, pp. 69-84 (1985).; Oja, E.: Principal components, minor components, and linear neural networks. Neural Networks 5, pp. 927 - 935 (1992).
Papers on nonlinear PCA and ICA: Hyvärinen, A. and Oja, E.: Independent Component Analysis by General Nonlinear Hebbian-like Learning Rules. Signal Processing 64 64}, pp. 301 - 313 (1998).; Hyvärinen, A. and Oja, E.: A Fast Fixed-Point Algorithm for Independent Component Analysis. Neural Computation 9, pp. 1483 - 1492 (1997).; Hyvärinen, A. and Oja, E.: One-Unit Learning Rules for Independent Component Analysis. Advances in Neural Information Processing Systems 9, MIT Press, pp. 480--486 (1997).; Oja, E.: The nonlinear PCA learning rule in Independent Component Analysis (draft). Neurocomputing 17, pp. 25 - 45 (1997).; Karhunen, J., Oja, E., Wang, L., Vigario, R., and Joutsensalo, J.: A class of neural networks for Independent Component Analysis (draft). IEEE Trans. on Neural Networks 8, pp. 486 - 504 (1997).; Hyvärinen, A. and Oja, E.: Simple neuron models for Independent Component Analysis. Int. J. Neural Systems 7, pp. 671 - 687 (1996).; Oja, E. and Wang, L.: Neural fitting: robustness by anti-Hebbian learning (draft). Neurocomputing 12, pp. 155 - 170 (1996).; Oja, E. and Wang, L.: Robust fitting by nonlinear neural units (draft). Neural Networks 9, pp. 435 - 444 (1996).; Oja, E., Karhunen, J., Wang, L., and Vigario, R.:Principal and independent components in neural networks - recent developments. Proc. VII Italian Workshop on Neural Nets WIRN'95, May 18 - 20, 1995, Vietri sul Mare, Italy (1995).; Oja, E.:The nonlinear PCA learning rule and signal separation - mathematical analysis. Helsinki University of Technology, Laboratory of Computer and Information Science, Report A26 (1995).; Oja, E.: PCA, ICA, and nonlinear Hebbian learning. Proc. Int. Conf. on Artificial Neural Networks ICANN-95, Oct. 9 - 13, 1995, Paris, France, pp. 89 - 94 (1995).; Oja, E. and Karhunen, J.:Signal separation by nonlinear Hebbian learning. In M. Palaniswami, Y. Attikiouzel, R. Marks II, D. Fogel, and T. Fukuda (Eds.), Computational Intelligence - a Dynamic System Perspective. New York: IEEE Press, pp. 83 - 97 (1995).; (More papers can be found on the home pages of the members of the ICA research group).

Erkki Oja: Older PCA / ICA papers available on-line

Erkki Oja:

Older PCA / ICA papers available on-line