Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
SpringerLink
Log in

Mathematical theory of neural learning

  • Special Issue
  • Published:
New Generation Computing Aims and scope Submit manuscript

Abstract

A mathematical theory of learning is presented in a unified manner to be applicable to various architectures of networks. The theory is based on parameter modification driven by a time series of input signals generated from a stochastic information source. A network modifies its behavior such that it adapts to the environmental information structure. The theory is self-organization of a neural system. A typical discrete structure is automatically formed through continuous parameter modification by self-organization.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. S. Amari. Mathematical foundations of neurocomputing.Proc. IEEE Special Issue on Neural Networks, 78:1443–1463, September 1990.

    Google Scholar 

  2. S. Amari. Theory of adaptive pattern classifiers.IEEE Trans., EC-16(3):299–307, 1967.

    MATH  MathSciNet  Google Scholar 

  3. S. Amari. Neural theory of association and concept-formation.Biological Cybernetics, 26:175–185, 1977.

    Article  MATH  MathSciNet  Google Scholar 

  4. D.J. Willshaw and S. von der Malsburg, C.Amari. How patterned neural connections can be set up by self-organization.Proc. Roy. Soc., B-194:431–445, 1976.

    Article  Google Scholar 

  5. S. Amari. Topographic organization of nerve fields.Bull. of Math. Biology, 42:339–364, 1980.

    MATH  MathSciNet  Google Scholar 

  6. A. Takeuchi and S. Amari. Formation of topographic maps and columnar microstructures.Biol. Cybernetics, 35:63–72, 1979.

    Article  MATH  MathSciNet  Google Scholar 

  7. E. Bienenstock, L.N. Cooper, and P.W. Munro. A theory for the development of neuron selectivity: Orientation specificity and binocular interaction in the visual cortex.J. Neuroscience, 2:32–48, 1982.

    Google Scholar 

  8. T. Kohonen. Self-organized formation of topologically correct feature maps.Biol. Cybernetics, 43:59–69, 1982.

    Article  MATH  MathSciNet  Google Scholar 

  9. T. Kohonen.Associative Memory and Self-organization. Springer-Verlag, 1984.

  10. S. Amari. Field theory of self-organizing neural nets.IEEE Trans. Systems, Man and Cybernetics, SMC-13(9 & 10):741–748, 1983.

    MATH  MathSciNet  Google Scholar 

  11. S. Amari. Mathematical theory on formation of category detecting nerve cells.Biol. Cybernetics, 29:127–136, 1978.

    Article  MATH  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mathematical Engineering and Information Physics Faculty of Engineering, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, 113, Tokyo, Japan

    Shun-ichi Amari

Authors
  1. Shun-ichi Amari
    View author publications

    You can also search for this author in PubMed Google Scholar

About this article

Cite this article

Amari, Si. Mathematical theory of neural learning. NGCO 8, 281–294 (1991). https://doi.org/10.1007/BF03037088

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF03037088

Keywords

Search

Navigation