A vector matrix real time recursive backpropagation algorithm for recurrent neural networks that approximate multi-valued periodic functions

DOI10.1142/S1469026809002667MaRDI QIDQ3401065zbMATH OpenFDO

Authors Peter A. Stubberud

Publication date 28 January 2010

Published in International Journal of Computational Intelligence and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1142/S1469026809002667

zbMATH Keywords

globally recurrent neural networkhysteresismulti-valued periodic functionsreal time recursive backpropagationrecurrent neural networksystem approximation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• scientific article; zbMATH DE number 2058635
• Approximation of dynamical systems by recurrent neural networks
• Multilayer feedforward networks are universal approximators
• scientific article; zbMATH DE number 1190938
• Approximation of state-space trajectories by locally recurrent globally feed-forward neural networks

Cites work

• Application of adjoint operators to neural learning
• scientific article; zbMATH DE number 559013 (Why is no real title available?)
• Multilayer feedforward networks are universal approximators

Cited in

(3)

• Accelerating a recurrent neural network to finite-time convergence using a new design formula and its application to time-varying matrix square root
• A Complex-Valued RTRL Algorithm for Recurrent Neural Networks
• Design of continuous-time recurrent neural networks with piecewise-linear activation function for generation of prescribed sequences of bipolar vectors

This page was built for publication: A vector matrix real time recursive backpropagation algorithm for recurrent neural networks that approximate multi-valued periodic functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3401065)