scientific article; zbMATH DE number 1016954

MaRDI QIDQ4339063zbMATH OpenFDO

Authors James J. Buckley, Esfandiar Eslami

Publication date 8 June 1997

zbMATH Keywords

function approximationfuzzy functionfuzzy neural netstriangular fuzzy numbers

Mathematics Subject Classification ID

Approximations and expansions (41A99) Learning and adaptive systems in artificial intelligence (68T05)

Review text

For fuzzy neural nets, i.e. layered, feedforward, neural nets with fuzzy weights or fuzzy signals, the authors discuss the problem of their approximation capabilities for given fuzzy functions, i.e. functions mapping triangular fuzzy numbers to triangular fuzzy numbers. They get partly positive, but mainly negative results for universal approximability. For the entire collection see [Zbl 0863.00023].

Recommendations

• Can fuzzy neural nets approximate continuous fuzzy functions?
• Universal approximators for fuzzy functions
• The fuzzy neural network approximation lemma
• A novel fuzzy neural network and its approximation capability

Cited in

(9)

• Universal approximators for fuzzy functions
• Is bias dispensable for fuzzy neural networks?
• Generalization capability of neural networks based on fuzzy operators
• scientific article; zbMATH DE number 1016955 (Why is no real title available?)
• scientific article; zbMATH DE number 1548382 (Why is no real title available?)
• scientific article; zbMATH DE number 1383064 (Why is no real title available?)
• Weights direct determination of triangular fuzzy feed-forward neural networks
• scientific article; zbMATH DE number 5051719 (Why is no real title available?)
• Advances in Neural Networks – ISNN 2005

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4339063)