Emergence of invariant-feature detectors in the adaptive-subspace self-organizing map

Abstract. A new self-organizing map (SOM) architecture called the ASSOM (adaptive-subspace SOM) is shown to create sets of translation-invariant filters when randomly displaced or moving input patterns are used as training data. No analytical functional forms for these filters are thereby postulated. Different kinds of filters are formed by the ASSOM when pictures are rotated during learning, or when they are zoomed. The ASSOM can thus act as a learning feature-extraction stage for pattern recognizers, being able to adapt to many sensory environments and to many different transformation groups of patterns.

[1]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[2]  Dennis Gabor,et al.  Theory of communication , 1946 .

[3]  Max V. Mathews,et al.  A linear coding for transmitting a set of correlated signals , 1956, IRE Trans. Inf. Theory.

[4]  Keinosuke Fukunaga,et al.  Application of the Karhunen-Loève Expansion to Feature Selection and Ordering , 1970, IEEE Trans. Computers.

[5]  Tzay Y. Young,et al.  Classification, Estimation and Pattern Recognition , 1974 .

[6]  Charles W. Therrien.  Eigenvalue Properties of Projection Operators and Their Application to the Subspace Method of Feature Extraction , 1975, IEEE Transactions on Computers.

[7]  Theodosios Pavlidis,et al.  Structural pattern recognition , 1977 .

[8]  Heikki Riittinen,et al.  Spectral classification of phonemes by learning subspaces , 1979, ICASSP.

[9]  J. Daugman.  Two-dimensional spectral analysis of cortical receptive field profiles , 1980, Vision Research.

[10]  S Marcelja,et al.  Mathematical description of the responses of simple cortical cells. , 1980, Journal of the Optical Society of America.

[11]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .

[12]  Erkki Oja,et al.  Subspace methods of pattern recognition , 1983 .

[13]  R. Gray,et al.  Vector quantization , 1984, IEEE ASSP Magazine.

[14]  J. Daugman.  Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[15]  J. Makhoul,et al.  Vector quantization in speech coding , 1985, Proceedings of the IEEE.

[16]  J. P. Jones,et al.  An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[17]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[18]  T. Kohonen,et al.  Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[19]  J. Rubner,et al.  A Self-Organizing Network for Principal-Component Analysis , 1989 .

[20]  Erol Gelenbe,et al.  Computer and Information Sciences - 3 , 1989 .

[21]  Ingrid Daubechies,et al.  The wavelet transform, time-frequency localization and signal analysis , 1990, IEEE Trans. Inf. Theory.

[22]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[23]  Erkki Oja,et al.  Principal components, minor components, and linear neural networks , 1992, Neural Networks.

[24]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[25]  Teuvo Kohonen,et al.  Physiological interpretationm of the self-organizing map algorithm , 1993 .

[26]  Teuvo Kohonen,et al.  Physiological interpretation of the Self-Organizing Map algorithm , 1993, Neural Networks.

[27]  Samuel Kaski,et al.  Winner-take-all networks for physiological models of competitive learning , 1994, Neural Networks.

[28]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[29]  Teuvo Kohonen,et al.  Learning vector quantization , 1998 .