UNIFIED FRAMEWORK FOR MLPs AND RBFNs: INTRODUCING CONIC SECTION FUNCTION NETWORKS

DOI10.1080/01969729408902340zbMath0939.68751OpenAlexW2043808819MaRDI QIDQ4840224

Georg Dorfdner

Publication date: 10 September 1995

Published in: Cybernetics and Systems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/01969729408902340

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items (3)

Many regression algorithms, one unified model: a review ⋮ Using radial basis function networks for function approximation and classification ⋮ Reduction of complexity in conic section function neural network

Cites Work

• Networks and the best approximation property
• Multilayer feedforward networks are universal approximators
• Neural Networks for Localized Approximation
• Automatische Klassifikation
• Approximation by superpositions of a sigmoidal function

This page was built for publication: UNIFIED FRAMEWORK FOR MLPs AND RBFNs: INTRODUCING CONIC SECTION FUNCTION NETWORKS