Learning in presence of input noise using the stochastic EM algorithm

DOI10.1063/1.1570540zbMATH Open1446.62350OpenAlexW1499496786MaRDI QIDQ5116318FDOQ5116318

Ali Mohammad-Djafari, Hichem Snoussi, Gilles Fleury, Abd-Krim Seghouane

Publication date: 24 August 2020

Published in: AIP Conference Proceedings (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1063/1.1570540

Recommendations

• Dynamic learning with the EM algorithm for neural networks
• scientific article; zbMATH DE number 2111322
• Neural network modelling with input uncertainty: Theory and application
• Maximum likelihood identification of noisy input-output models
• Learning under signal-to-noise ratio uncertainty

zbMATH Keywords

neural networklearning algorithm

Mathematics Subject Classification ID

Statistical aspects of big data and data science (62R07) Learning and adaptive systems in artificial intelligence (68T05) Neural nets and related approaches to inference from stochastic processes (62M45)

Cited In (8)

• Learning under signal-to-noise ratio uncertainty
• Dynamic learning with the EM algorithm for neural networks
• Theory and Applications of Models of Computation
• Neural network modelling with input uncertainty: Theory and application
• Learning juntas in the presence of noise
• Title not available (Why is that?)
• Effect of wrong samples on the convergence of learning processes
• Title not available (Why is that?)

This page was built for publication: Learning in presence of input noise using the stochastic EM algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5116318)