Two k-winners-take-all networks with discontinuous activation functions

DOI10.1016/J.NEUNET.2007.12.044MaRDI QIDQ1932004zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Qingshan Liu, Jun Wang

Publication date 17 January 2013

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2007.12.044

zbMATH Keywords

differential inclusiondiscontinuous activation functionglobal convergencelinear programmingLyapunov stabilityquadratic programmingrecurrent neural network

Mathematics Subject Classification ID

Linear programming (90C05) Quadratic programming (90C20) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• KWTA networks and their applications
• Analysis and design of a distributed \(k\)-winners-take-all model
• A model of analogue K-winners-take-all neural circuit
• Winner-take-all networks for physiological models of competitive learning
• On a constant-time, low-complexity winner-take-all neural network

Cites work

• A Neural Network With<tex>$O(N)$</tex>Neurons for Ranking<tex>$N$</tex>Numbers in<tex>$O(1/N)$</tex>Time
• Dynamical Behaviors of Delayed Neural Network Systems with Discontinuous Activation Functions
• Global convergence of neural networks with discontinuous neuron activations
• scientific article; zbMATH DE number 417962 (Why is no real title available?)
• scientific article; zbMATH DE number 3855514 (Why is no real title available?)
• scientific article; zbMATH DE number 41285 (Why is no real title available?)
• Matrix Analysis
• Optimization and nonsmooth analysis
• Stable computational dynamics for a class of circuits with O(N) interconnections capable of KWTA and rank extractions

Cited in

(10)

• A non-penalty recurrent neural network for solving a class of constrained optimization problems
• KWTA networks and their applications
• Analysis and design of a distributed \(k\)-winners-take-all model
• A model of analogue K-winners-take-all neural circuit
• A Novel Recurrent Neural Network with Finite-Time Convergence for Linear Programming
• Existence and uniqueness of KWTA-solutions for a neural network mathematical model of processing sampled signals
• A \(k\)-winner-takes-all classifier for structured data
• Single-state distributed \(k\)-winners-take-all neural network model
• Distributed \(k\)-winners-take-all via multiple neural networks with inertia
• A novel competition model for dynamic winner-take-all

This page was built for publication: Two \(k\)-winners-take-all networks with discontinuous activation functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1932004)