A fixed-distribution PAC learning theory for neural FIR models

DOI10.1007/s10844-005-0194-yzbMath1093.68087OpenAlexW2017612368MaRDI QIDQ2490395

Kayvan Najarian

Publication date: 2 May 2006

Published in: Journal of Intelligent Information Systems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10844-005-0194-y

zbMATH Keywords

FIR three-layer feedforward sigmoid neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

An automated optimal engagement and attention detection system using electrocardiogram

Cites Work

• Unnamed Item
• Unnamed Item
• Learnability with respect to fixed distributions
• Approximation and estimation bounds for artificial neural networks
• On stochastic stability of dynamic neural models in presence of noise
• Learning theory applied to sigmoid network classification of protein biological function using primary protein structure
• Learning-based complexity evaluation of radial basis function networks
• FIR Volterra kernel neural models and PAC learning
• PAC learning in non-linear FIR models
• A theory of the learnable

This page was built for publication: A fixed-distribution PAC learning theory for neural FIR models