Networks that approximate vector-valued mappings

Ferdinando A. Mussa-Ivaldi*, Francesca Gandolfo

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations


We propose a network architecture capable of approximating an arbitrary pattern of vectors by a linear superposition of non-linear vector fields. Our approach is based on a direct extension of the method of basis functions to the representation of vector-valued mappings. In the proposed network architecture vector approximation is represented as a form of auto-association: the output field must reproduce as closely as possible the set of input vectors. We show that with a simple and relatively small set of connection weights it is possible to represent a board spectrum of vector patterns and to generate a functionally meaningful decomposition of these patterns into zero-curl and zero-divergence components.

Original languageEnglish (US)
Title of host publication1993 IEEE International Conference on Neural Networks
PublisherPubl by IEEE
Number of pages6
ISBN (Electronic)0780309995
ISBN (Print)0780312007
StatePublished - Jan 1 1993
Event1993 IEEE International Conference on Neural Networks - San Francisco, California, USA
Duration: Mar 28 1993Apr 1 1993

Publication series

Name1993 IEEE International Conference on Neural Networks


Other1993 IEEE International Conference on Neural Networks
CitySan Francisco, California, USA

ASJC Scopus subject areas

  • Engineering(all)
  • Control and Systems Engineering
  • Software
  • Artificial Intelligence


Dive into the research topics of 'Networks that approximate vector-valued mappings'. Together they form a unique fingerprint.

Cite this