ArticlesNo Access

A New Modulated Hebbian Learning Rule — Biologically Plausible Method for Local Computation of a Principal Subspace

Control Department, The Institute of Electrical Engineering "Nikola Tesla", Koste Glavinica 8a, 11000 Belgrade, Serbia and Montenegro

Search for more papers by this author

and

Hidemitsu Ogawa

Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan 152-8552, Japan

Search for more papers by this author

https://doi.org/10.1142/S0129065703001595Cited by:7 (Source: Crossref)

Abstract

This paper presents one possible implementation of a transformation that performs linear mapping to a lower-dimensional subspace. Principal component subspace will be the one that will be analyzed. Idea implemented in this paper represents generalization of the recently proposed ∞OH neural method for principal component extraction. The calculations in the newly proposed method are performed locally — a feature which is usually considered as desirable from the biological point of view. Comparing to some other wellknown methods, proposed synaptic efficacy learning rule requires less information about the value of the other efficacies to make single efficacy modification. Synaptic efficacies are modified by implementation of Modulated Hebb-type (MH) learning rule. Slightly modified MH algorithm named Modulated Hebb Oja (MHO) algorithm, will be also introduced. Structural similarity of the proposed network with part of the retinal circuit will be presented, too.

Keywords:

References

J. J. Atick and A. N. Redlich, Neural Computation 3, 308 (1990). Google Scholar
J. J. Atick and A. N. Redlich, Neural Computation 4, 196 (1992). Crossref, Web of Science, Google Scholar
J. J. Atick and A. N. Redlich, Neural Computation 5, 45 (1993). Crossref, Web of Science, Google Scholar
P. Baldi and K. Hornik, IEEE Trans. Neural Networks 6, 837 (1995). Crossref, Medline, Web of Science, Google Scholar
C. Chatterjee, Z. Kang and V. P. Roychowdhury, IEEE Trans. Neural Networks 11(2), 338 (2000). Crossref, Medline, Web of Science, Google Scholar
T. Chen, Y. Hua and W. Yan, IEEE Trans. Neural Networks 9(1), 58 (1998). Crossref, Medline, Web of Science, Google Scholar
G. Deco and D. Obradovic , An information-theoretic approach to neural computing ( Springer-Verlag New York Inc. , 1996 ) . Crossref, Google Scholar
K. I. Diamantaras, Robust principal component extracting neural networks, ICNN'96 (1996) pp. 74–77. Google Scholar
S. C. Douglas, S. Y. Kung and S. Amari, IEEE Signal Processing Letters 5(12), 328 (1998). Crossref, Web of Science, Google Scholar
J. Dowling , The Retina: An approachable part of the brain ( The Belknap Press of Harward University Press , 1987 ) . Google Scholar
S. Fiori, Neural Computation 13(7), 1625 (2001). Crossref, Web of Science, Google Scholar
C. Fyfe and R. J. Baddeley, Network: Computation in Neural Systems 6(3), 334 (1995). Google Scholar
C. Fyfe and R. J. Baddeley, Biological Cybernetics 72(6), 533 (1995). Crossref, Web of Science, Google Scholar
M. C. Goodall, Nature 185, 557 (1960). Crossref, Web of Science, Google Scholar
G. F. Harpur and R. W. Prager 1994, "Experiments with simple Hebbian-based learning rules in pattern classification tasks," Technical report CUED/F-INFENG/TR 168 (Cambridge University Engineering Department, UK) . Google Scholar
G. F. Harpur 1997, "Low entropy coding with unsupervised neural networks" (Ph.D. thesis, Cambridge University Engineering Department, UK) . Google Scholar
M. Jankovic , A new simple ∞OH neuron model as a principal component analyzer , CCECE'01 ( 2001 ) . Google Scholar
L. Ljung, IEEE Trans. Automat. Contr. 22, 551 (1977). Crossref, Web of Science, Google Scholar
H. Ogawa, Karhunen-Loé ve Subspace, International Conference on Pattern Recognition (1992) pp. 75–78. Google Scholar
E. Oja, J. Math. Biol. 15, 267 (1982). Crossref, Medline, Web of Science, Google Scholar
E. Oja , Subspace method of pattern recognition ( Research Studies Press and J. Wiley , Letchworth , 1983 ) . Google Scholar
E. Oja, Int. J. Neural Systems 1, 61 (1989). Link, Web of Science, Google Scholar
E. Oja and J. Karhunen, J. Math. Anal. Appl. 106, 69 (1985). Crossref, Web of Science, Google Scholar
E. Oja, H. Ogawa and J. Wangviwattana, IEICE Trans. Inf.&Syst. E75-D(3), 366 (1992). Google Scholar
E. Oja, H. Ogawa and J. Wangviwattana, IEICE Trans. Inf.&Syst. E75-D(3), 376 (1992). Google Scholar
S. Ouyang, Z. Bao and G. Liao, IEEE Trans. Neural Networks 11(1), 215 (2000). Crossref, Medline, Web of Science, Google Scholar
M. Plumbley 1991, "On information theory and unsupervised neural networks," Technical Report CUED/F-INFENG/TR 78 (Cambridge University Engineering Department, UK) . Google Scholar
A. Weingessel and K. Hornik, IEEE Trans. Neural Networks 11(6), 1242 (2000). Crossref, Medline, Web of Science, Google Scholar
L. Xu, Neural Networks 6, 627 (1993). Crossref, Web of Science, Google Scholar
W. Yan, U. Helmke and J. B. Moore, IEEE Trans. Neural Networks 5(5), 674 (1994). Medline, Web of Science, Google Scholar
Q. Zhang and Y. Leung, IEEE Trans. Neural Networks 11(2), 529 (2000). Crossref, Medline, Web of Science, Google Scholar