A Complex-Valued RTRL Algorithm for Recurrent Neural Networks

DOI10.1162/0899766042321779MaRDI QIDQ4664519zbMATH OpenOpenAlexWikidataFDO

Authors Su Lee Goh, Danilo P. Mandic

Publication date 5 April 2005

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/0899766042321779

zbMATH Keywords

Complex-valued Real-Time Rercurrent Learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonnumerical algorithms (68W05)

Recommendations

• An augmented CRTRL for complex-valued recurrent neural networks
• Complex-valued recurrent neural network with IIR neuron model: Training and applications.
• Complex-valued neural networks
• Complex recurrent neural network for computing the inverse and pseudo-inverse of the complex matrix
• An Augmented Extended Kalman Filter Algorithm for Complex-Valued Recurrent Neural Networks
• Complex-valued neural networks. Advances and applications
• Convergence analysis of three classes of Split-complex gradient algorithms for complex-valued recurrent neural networks
• A vector matrix real time recursive backpropagation algorithm for recurrent neural networks that approximate multi-valued periodic functions

Cites work

• Approximation by Fully Complex Multilayer Perceptrons
• Complex domain backpropagation

Cited in

(19)

• Proposal of relative-minimization learning for behavior stabilization of complex-valued recurrent neural networks
• A normalised real time recurrent learning algorithm.
• Global exponential periodicity and stability of discrete-time complex-valued recurrent neural networks with time-delays
• Convergence analysis of an augmented algorithm for fully complex-valued neural networks
• Matrix measure method for global exponential stability of complex-valued recurrent neural networks with time-varying delays
• A novel nonlinear adaptive filter using a pipelined second-order Volterra recurrent neural network
• Fully complex multi-layer perceptron network for nonlinear signal processing
• Complex-valued recurrent neural network with IIR neuron model: Training and applications.
• Complex-valued wavelet network
• A meta-cognitive learning algorithm for a fully complex-valued relaxation network
• An augmented CRTRL for complex-valued recurrent neural networks
• Multistability of complex-valued neural networks with discontinuous activation functions
• Convergence analysis of three classes of Split-complex gradient algorithms for complex-valued recurrent neural networks
• An Augmented Extended Kalman Filter Algorithm for Complex-Valued Recurrent Neural Networks
• Data-Reusing Recurrent Neural Adaptive Filters
• scientific article; zbMATH DE number 795148 (Why is no real title available?)
• Wind direction modelling using multiple observation points
• A complex-valued neural dynamical optimization approach and its stability analysis
• Complex-valued adaptive signal processing using nonlinear functions

This page was built for publication: A Complex-Valued RTRL Algorithm for Recurrent Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4664519)