Analysis of the convergence properties of self-normalized source separation neural networks

DOI10.1109/78.757215MaRDI QIDQ2723618zbMATH OpenOpenAlexFDO

Authors Yannick Deville

Publication date 8 July 2001

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/78.757215

zbMATH Keywords

equilibrium pointsHérault-Jutten networkseparation neural networkstabilitystationary independent sourcessuper-Gaussian source signals

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Recommendations

• Analysis of the stability of a self-normalized adaptive source separation neural network
• New self-normalized blind source separation networks for instantaneous and convolutive mixtures
• Transpose properties in the stability and performance of the classic adaptive algorithms for blind source separation and deconvolution.
• Self-adaptive separation of convolutively mixed signals with a recursive structure. I: Stability analysis and optimization of asymptotic behaviour
• Blind source separation and equiprobabilistic topographic maps

Cited in

(4)

• Recurrent networks for separating extractable-target nonlinear mixtures. I. Non-blind configurations
• Single channel source separation using time-frequency non-negative matrix factorization and sigmoid base normalization deep neural networks
• Analysis of the stability of a self-normalized adaptive source separation neural network
• New self-normalized blind source separation networks for instantaneous and convolutive mixtures

This page was built for publication: Analysis of the convergence properties of self-normalized source separation neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2723618)