Loading [a11y]/accessibility-menu.js
Networks for approximation and learning | IEEE Journals & Magazine | IEEE Xplore

Networks for approximation and learning


Abstract:

The problem of the approximation of nonlinear mapping, (especially continuous mappings) is considered. Regularization theory and a theoretical framework for approximation...Show More

Abstract:

The problem of the approximation of nonlinear mapping, (especially continuous mappings) is considered. Regularization theory and a theoretical framework for approximation (based on regularization techniques) that leads to a class of three-layer networks called regularization networks are discussed. Regularization networks are mathematically related to the radial basis functions, mainly used for strict interpolation tasks. Learning as approximation and learning as hypersurface reconstruction are discussed. Two extensions of the regularization approach are presented, along with the approach's corrections to splines, regularization, Bayes formulation, and clustering. The theory of regularization networks is generalized to a formulation that includes task-dependent clustering and dimensionality reduction. Applications of regularization networks are discussed.<>
Published in: Proceedings of the IEEE ( Volume: 78, Issue: 9, September 1990)
Page(s): 1481 - 1497
Date of Publication: 06 August 2002

ISSN Information:


Contact IEEE to Subscribe

References

References is not available for this document.