How Lateral Interaction Develops in a Self-Organizing Feature Map

  title={How Lateral Interaction Develops in a Self-Organizing Feature Map},
  author={Joseph Sirosh and Risto Miikkulainen},
| A biologically motivated mechanism for self-organizing a neural network with modi able lateral connections is presented. The weight modi cation rules are purely activity-dependent, unsupervised and local. The lateral interaction weights are initially random but develop into a \Mexican hat" shape around each neuron. At the same time, the external inputweights self-organize to form a topological map of the input space. The algorithm demonstrates how self-organization can bootstrap itself using… CONTINUE READING
17 Extracted Citations
13 Extracted References
Similar Papers

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 13 references

Cortical Circuits: Synaptic Organization of the Cerebral Cortex|Structure

  • E. L. White
  • Function, and Theory,
  • 1989
Highly Influential
3 Excerpts

Convergence properties of self-organizing maps,

  • E. Erwin, K. Obermayer, K. J. Schulten
  • Proceedings of the International Conference on…
  • 1991
1 Excerpt

Self-Organization and Associative Memory, 3rd ed

  • T. Kohonen
  • New York: Springer,
  • 1989
3 Excerpts

Principles of cortical network organization,

  • C. von der Malsburg, W. Singer
  • Neurobiology of Neocortex,
  • 1988
2 Excerpts

Similar Papers

Loading similar papers…