Self-organized formation of topologically correct feature maps

  title={Self-organized formation of topologically correct feature maps},
  author={Teuvo Kohonen},
  journal={Biological Cybernetics},
  • T. Kohonen
  • Published 2004
  • Mathematics, Computer Science
  • Biological Cybernetics
This work contains a theoretical study and computer simulations of a new self-organizing process. The principal discovery is that in a simple network of adaptive physical elements which receives signals from a primary event space, the signal representations are automatically mapped onto a set of output responses in such a way that the responses acquire the same topological order as that of the primary events. In other words, a principle has been discovered which facilitates the automatic… Expand
Topological feature maps with self-organized lateral connections: a population-coded, one-layer model of associative memory
A simple, neural, one-layer model for auto-association that is capable of performing a cluster analysis and hierarchical classification of data and qualifies as a tool for unsupervised statistical data analysis. Expand
Self–organized maps of sensory events
  • T. Kohonen
  • Computer Science
  • Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences
  • 2003
This paper shall discuss a special type of data–driven self–organization, namely, automatic formation of ordered, compressed representations of sensory events that are learned in a process that involves competition between sets of neural cells on common input data, and sensitization or tuning of the most strongly responding cells and their local neighbours to this input. Expand
Lateral Interactions in Self-Organizing Maps
A novel lateral interaction model will be presented here, whose investigation will show that the behavior of the two models is not identical; and that the lateral interaction architecture behaves similarly to non-topographic algorithms, constructing representations of the input at intermediate levels of detail in the initial phases of training. Expand
Recursive Self-organizing Map as a Contractive Iterative Function System
It is shown that contractive fixed input maps are likely to produce Markovian organizations of receptive fields on the RecSOM map, and bounds on parameter β (weighting the importance of importing past information when processing sequences) under which contractiveness of the fixedinput maps is guaranteed are derived. Expand
Self-organizing semantic maps
Self-organized formation of topographic maps for abstract data, such as words, is demonstrated and it is argued that a similar process may be at work in the brain. Expand
Transition times in self-organizing maps
  • T. Heskes
  • Computer Science, Mathematics
  • Biological Cybernetics
  • 2004
A self-organizing learning rule is considered which is equivalent to the Kohonen learning rule, except for the determination of the ‘winning’ unit and the existence of an error potential facilitates a global description of the learning process. Expand
Self-Organizing Maps with Asymmetric Neighborhood Function
It is demonstrated that the distortion of the map can be suppressed by improving the asymmetric neighborhood function SOM algorithm, and the number of learning steps required for perfect ordering in the case of the one-dimensional SOM is numerically shown to be reduced from O(N3) to O( N2) with an asymmetricNeighborhood function. Expand
A self-organizing neural network sharing features of the mammalian visual system
It is shown by computer simulation that a process of self-organization that departs from a fixed retinotopic order at peripheral layers and includes hebbian modifications of synaptic connectivity at higher processing levels leads to a system that is capable of mimicking various functions of visual systems. Expand
Phase diagrams of self-organizing maps.
  • Bauer, Riesenhuber, Geisel
  • Physics, Medicine
  • Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics
  • 1996
We present a method which allows the analytic determination of phase diagrams in the self-organizing map, a model for the formation of topographic projection patterns in the brain and in signalExpand
Self-organized patterns in the SOM network
  • Ruye Wang
  • Computer Science
  • 2015 11th International Conference on Natural Computation (ICNC)
  • 2015
The discovery of certain self-organized patterns that develop automatically and unexpectedly during the training of a typical self-organizing map (SOM) network and speculates and hypothesizes the possible mechanism based on some qualitative and heuristic studies. Expand


How patterned neural connections can be set up by self-organization
Without needing to make any elaborate assumptions about its structure or about the operations its elements are to carry out, it is shown that the mappings are set up in a system- to-system rather than a cell-to-cell fashion. Expand
Self-organization of orientation sensitive cells in the striate cortex
A nerve net model for the visual cortex of higher vertebrates is presented. A simple learning procedure is shown to be sufficient for the organization of some essential functional properties ofExpand
Topographic organization of nerve fields
  • S. Amari
  • Medicine, Geology
  • Neuroscience Letters
  • 1979
A mathematical theory of the functional dynamics of cortical and thalamic nervous tissue
It is shown that this particular mode reproduces some of the phenomenology of visual psychophysics, including spatial modulation transfer function determinations, certain metacontrast effects, and the spatial hysteresis phenomenon found in stereopsis. Expand
Modality and topographic properties of single neurons of cat's somatic sensory cortex.
Observations upon the modality and topographical attributes of single neurons of the first somatic sensory area of the cat’s cerebral cortex, the analogue of the cortex of the postcentral gyrus in the primate brain, support an hypothesis of the functional organization of this cortical area. Expand
A marker induction mechanism for the establishment of ordered neural mappings: its application to the retinotectal problem.
  • D. Willshaw, C. von der Malsburg
  • Computer Science, Medicine
  • Philosophical transactions of the Royal Society of London. Series B, Biological sciences
  • 1979
This paper examines the idea that ordered patterns of nerve connections are set up by means of markers carried by the individual cells, and suggests that the results of many of the regeneration experiments are manifestations of a conflict between the two alternative ways of specifying the orientation of the map. Expand
Principles of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms.
In recent years, there have been a number of engineering projects concerned with the design of brain models for pattern recognition and artificial intelligence. The basic assumption, underlying theseExpand
How to label nerve cells so that they can interconnect in an ordered fashion.
We present a method for setting up topographically ordered mappings between two sheets of nerve cells. A set of chemical markers that express the neighborhood relationships within the presynapticExpand
Notes on the hypothesis of columnar organization in somatosensory cerebral cortex.
  • A. Towe
  • Psychology, Medicine
  • Brain, behavior and evolution
  • 1975
If a columnar structure exists, it defies clear detection by current neurophysiological techniques and experimental approaches and, taken at face value, it is shown to yield some rather unusual predictions. Expand
A model for the formation of ocular dominance stripes
  • N. Swindale
  • Biology, Medicine
  • Proceedings of the Royal Society of London. Series B. Biological Sciences
  • 1980
A model of competition that explains the formation of the ocular dominance stripes found in layer IVc of cat and monkey visual cortex is described, which can be generalized to account for pattern formation in other systems, such as zebra or mackerel skin, where similar striped patterns occur. Expand