Universal Approximation Capability of Cascade Correlation for Structures

DOI10.1162/0899766053491878zbMath1096.68132OpenAlexW2151827881WikidataQ60670889 ScholiaQ60670889MaRDI QIDQ4678448

Barbara Hammer, Alessandro Sperduti, Alessio Micheli

Publication date: 23 May 2005

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/0899766053491878

zbMATH Keywords

acyclic graph structuresmeasurable function from tree structures

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (4)

Deep reservoir neural networks for trees ⋮ Comparison of relevance learning vector quantization with other metric adaptive classification methods ⋮ A gentle introduction to deep learning for graphs ⋮ From Hopfield nets to recursive networks to graph machines: numerical machine learning for structured data

Cites Work

• Feedforward nets for interpolation and classification
• Multilayer feedforward networks are universal approximators
• Spatiotemporal Connectionist Networks: A Taxonomy and Review
• Similarity learning for graph-based image representations

This page was built for publication: Universal Approximation Capability of Cascade Correlation for Structures