A Vision Architecture

Christoph von der Malsburg


We are offering a particular interpretation (well within the range of experimentally and theoretically accepted notions) of neural connectivity and dynamics and discuss it as the data-and-process architecture of the visual system. In this interpretation the permanent connectivity of cortex is an overlay of well-structured networks, “nets”, which are formed on the slow time-scale of learning by self-interaction of the network under the influence of sensory input, and which are selectively activated on the fast perceptual time-scale. Nets serve as an explicit, hierarchical representation of visual structure in the various sub-modalities, as constraint networks favouring mutually consistent sets of latent variables and as projection mappings to deal with invariance.


  1. Allman, J., Mieyin, F. and McGuinness, E., 1985. Stimulus specific responses from beyond the classical receptive field: neurophysiological mechanisms for local-global comparisons in visual neurons. Annu Rev Neurosci 8:407-30
  2. Anderson, C. H. and Van Essen, D. C., 1987). Shifter circuits: a computational strategy for dynamic aspects of visual processing. PNAS 84, 6297-6301.
  3. D.W. Arathorn D.W., 2002. Map-Seeking circuits in Visual Cognition -- A Computational Mechanism for Biological and Machine Vision. Standford Univ. Press, Stanford, California.
  4. Barlow, H.B., 1972. Single Units and Sensation: A Neuron Doctrine for Perceptual Psychology. Perception 1, 371-394.
  5. Biederman, I., 1987. Recognition-by-components: a theory of human image understanding. Psychol Rev. 94 115-147.
  6. Fukushima, K., 1980. Neocognitron: A Self-Organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by a Shift in Position.
  7. Kree, R. and Zippelius, A., 1988. Recognition of Topological Features of Graphs and Images in Neural Networks. J. Phys. A 21, 813-818.
  8. Lades, M., Vorbrüggen, J.C., Buhmann, J.. Lange, J., von der Malsburg, C., Würtz, R.P. Würtz and Konen, W., 1993. Distortion invariant object recognition in the dynamic link architecture. IEEE Transactions on Computers, 42:300-311.
  9. Olshausen, B.A. and Field, D.J., 1996. Emergence of simple-cell receptive fields properties by learning a sparse code for natural images. Nature 381, 607-609.
  10. Polsky, A. and Mel, B.W. And Schiller, J., 2004. Computational subunits in thin dendrites of pyramidal cells. Nature Neuroscience 7, 621-627.
  11. Shen-Orr, S.S., Milo, R., Mangan, S. and Alon, U., 2002. Network motifs in the transcriptional regulation network of Escherichia coli. Nature Genetics 31, 64- 68.
  12. P. Wolfrum, C. Wolff, J. Lücke, and C. von der Malsburg. A recurrent dynamic model for correspondence-based face recognition. Journal of Vision 8, 1--18. doi:10.1167/8.7.34, 2008.

Paper Citation

in Harvard Style

von der Malsburg C. (2014). A Vision Architecture . In Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2014) ISBN 978-989-758-054-3, pages 345-350. DOI: 10.5220/0005158103450350

in Bibtex Style

author={Christoph von der Malsburg},
title={A Vision Architecture},
booktitle={Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2014)},

in EndNote Style

JO - Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2014)
TI - A Vision Architecture
SN - 978-989-758-054-3
AU - von der Malsburg C.
PY - 2014
SP - 345
EP - 350
DO - 10.5220/0005158103450350