Sufficient conditions for one-dimensional cellular neural networks to perform connected component detection

DOI10.1016/J.NONRWA.2010.05.007MaRDI QIDQ708585zbMATH OpenOpenAlexFDO

Authors D. Kharzeev

Publication date 14 October 2010

Published in Nonlinear Analysis. Real World Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.nonrwa.2010.05.007

zbMATH Keywords

convergencelocal regularitytemplatecellular neural networkconnected component detection

Mathematics Subject Classification ID

Qualitative investigation and simulation of ordinary differential equation models (34C60) Neural networks for/in biological studies, artificial life and related topics (92B20) Asymptotic properties of solutions to ordinary differential equations (34D05)

Recommendations

• Stability of 1-D-CNN's with Dirichlet boundary conditions and global propagation dynamics
• Stability analysis of nonsymmetric cellular neural networks
• An approach to information propagation in 1-D cellular neural networks-Part I: Local diffusion
• On the OP‐amp based circuit design of cellular neural networks
• scientific article; zbMATH DE number 2233453

Cites work

• A new parameter range for the stability of opposite-sign cellular neural networks
• A rigorous design method for binary cellular neural networks
• An approach to information propagation in 1-D cellular neural networks-Part I: Local diffusion
• An approach to information propagation in 1-D cellular neural networks. II. Global propagation
• CNN cloning template: Shadow detector
• Cellular neural networks: theory
• Complex dynamics in one‐dimensional CNNs
• Influence of boundary conditions on the behavior of cellular neural networks
• On locally regular cellular neural networks
• Stability of 1-D-CNN's with Dirichlet boundary conditions and global propagation dynamics
• Stability of CNN with opposite-sign templates and nonunity gain output functions
• Stability of cellular neural networks with one-dimensional templates

Cited in

(3)

• On the structure of multi-layer cellular neural networks
• Design of continuous-time recurrent neural networks with piecewise-linear activation function for generation of prescribed sequences of bipolar vectors
• Global dynamic behaviour of a three‐cell connected component detector cnn

This page was built for publication: Sufficient conditions for one-dimensional cellular neural networks to perform connected component detection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q708585)