PAC learning in non-linear FIR models

DOI10.1002/1099-1115(200102)15:1%3C37::AID-ACS626%3E3.0.CO;2-7MaRDI QIDQ2708066zbMATH OpenOpenAlexFDO

Authors Kayvan Najarian, Guy A. Dumont, M. S. Davies, N. Heckman

Publication date 13 July 2001

Full work available at URL https://doi.org/10.1002/1099-1115(200102)15:1%3C37::aid-acs626%3E3.0.co;2-7

zbMATH Keywords

learningnonlinear finite impulse response modelsPAC learningprobabilistic methodsprobably approximately correct learning theory

Mathematics Subject Classification ID

Nonlinear systems in control theory (93C10) Stochastic learning and adaptive control (93E35)

Cites work

• A theory of the learnable
• scientific article; zbMATH DE number 3309776 (Why is no real title available?)
• Minimum complexity regression estimation with weakly dependent observations
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Recursive hybrid algorithm for non-linear system identification using radial basis function networks

Cited in

(2)

• A fixed-distribution PAC learning theory for neural FIR models
• An automated optimal engagement and attention detection system using electrocardiogram

This page was built for publication: PAC learning in non-linear FIR models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2708066)