FIR Volterra kernel neural models and PAC learning

DOI10.1002/CPLX.10042MaRDI QIDQ1860326zbMATH OpenOpenAlexFDO

Authors Kayvan Najarian

Publication date 20 February 2003

Published in Complexity (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1002/cplx.10042

zbMATH Keywords

\(m\)-dependencynonlinear FIR modelPAC learningVolterra kernel polynomials

Mathematics Subject Classification ID

Algorithmic information theory (Kolmogorov complexity, etc.) (68Q30) Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies and applications (68U99)

Review text

Summary: The probably approximately correct (PAC) learning theory creates a framework to assess the learning properties of static models for which the data are assumed to be independently and identically distributed (i.i.d.). The present article first extends the idea of PAC learning to cover the learning of modeling tasks with m-dependent sequences of data. The data are assumed to be marginally distributed according to a fixed arbitrary probability. The resulting framework is then applied to evaluate learning of Volterra Kernel FIR models.

Recommendations

• A fixed-distribution PAC learning theory for neural FIR models
• scientific article; zbMATH DE number 1696568
• scientific article; zbMATH DE number 926775
• scientific article; zbMATH DE number 503283
• An introduction to some statistical aspects of PAC learning theory

Cited in

(2)

• A fixed-distribution PAC learning theory for neural FIR models
• scientific article; zbMATH DE number 1696568 (Why is no real title available?)

This page was built for publication: FIR Volterra kernel neural models and PAC learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1860326)