Convergence properties of cascade correlation in function approximation.

DOI10.1007/BF01415010MaRDI QIDQ676876zbMATH OpenFDO

Authors Gian Paolo Drago, Sandro Ridella

Publication date 7 August 1997

Published in Neural Computing and Applications (Search for Journal in Brave)

zbMATH Keywords

Adaptive architectureGrowing neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• On the convergence of a growing topology neural algorithm
• An accelerated learning algorithm for a neural network with the cascade-correlation
• An incremental learning algorithm for function approximation
• The convergence of stochastic gradient algorithms applied to learning in neural networks
• Knowledge-based cascade-correlation: Using knowledge to speed learning

Cites work

• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Universal approximation bounds for superpositions of a sigmoidal function

Cited in

(7)

• Universal Approximation Capability of Cascade Correlation for Structures
• Evaluation of constructive neural networks with cascaded architectures
• Using the cascade-correlation algorithm to evaluate investment projects
• An accelerated learning algorithm for a neural network with the cascade-correlation
• scientific article; zbMATH DE number 2033145 (Why is no real title available?)
• Knowledge-based cascade-correlation: Using knowledge to speed learning
• Convergence analysis of convex incremental neural networks

This page was built for publication: Convergence properties of cascade correlation in function approximation.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q676876)