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.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
S. Amari. Mathematical foundations of neurocomputing.Proc. IEEE Special Issue on Neural Networks, 78:1443–1463, September 1990.
S. Amari. Theory of adaptive pattern classifiers.IEEE Trans., EC-16(3):299–307, 1967.
S. Amari. Neural theory of association and concept-formation.Biological Cybernetics, 26:175–185, 1977.
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.
S. Amari. Topographic organization of nerve fields.Bull. of Math. Biology, 42:339–364, 1980.
A. Takeuchi and S. Amari. Formation of topographic maps and columnar microstructures.Biol. Cybernetics, 35:63–72, 1979.
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.
T. Kohonen. Self-organized formation of topologically correct feature maps.Biol. Cybernetics, 43:59–69, 1982.
T. Kohonen.Associative Memory and Self-organization. Springer-Verlag, 1984.
S. Amari. Field theory of self-organizing neural nets.IEEE Trans. Systems, Man and Cybernetics, SMC-13(9 & 10):741–748, 1983.
S. Amari. Mathematical theory on formation of category detecting nerve cells.Biol. Cybernetics, 29:127–136, 1978.
Author information
Authors and Affiliations
About this article
Cite this article
Amari, Si. Mathematical theory of neural learning. NGCO 8, 281–294 (1991). https://doi.org/10.1007/BF03037088
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF03037088