Convergence analysis of an augmented algorithm for fully complex-valued neural networks

DOI10.1016/J.NEUNET.2015.05.003zbMath1401.68271OpenAlexW776779855WikidataQ50901832 ScholiaQ50901832MaRDI QIDQ1669147

Huisheng Zhang, Danilo P. Mandic, Dong-po Xu

Publication date: 30 August 2018

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2015.05.003

zbMATH Keywords

convergencecomplex-valued neural networksWirtinger calculusaugmented algorithmunified mean value theorem

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) PDEs in connection with computer science (35Q68)

Related Items (7)

Smoothed \(L_{1/2}\) regularizer learning for split-complex valued neuro-fuzzy algorithm for TSK system and its convergence results ⋮ Fully complex conjugate gradient-based neural networks using Wirtinger calculus framework: deterministic convergence and its application ⋮ Parameter-range-dependent robust stability conditions for quaternion-valued neural networks with time delays ⋮ Widely linear complex-valued least mean M-estimate algorithms: design and performance analysis ⋮ Convergence analysis of AdaBound with relaxed bound functions for non-convex optimization ⋮ Convergence of the RMSProp deep learning method with penalty for nonconvex optimization ⋮ Exponential synchronization for second-order nodes in complex dynamical network with communication time delays and switching topologies

Cites Work

• Unnamed Item
• Batch gradient method with smoothing \(L_{1/2}\) regularization for training of feedforward neural networks
• Complex-valued neural networks with multi-valued neurons.
• Convergence analysis of online gradient method for BP neural networks
• Complex-valued neural networks
• Convergence of batch split-complex backpropagation algorithm for complex-valued neural networks
• An augmented CRTRL for complex-valued recurrent neural networks
• 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
• Complex Valued Nonlinear Adaptive Filters
• Complex domain backpropagation
• Complex ICA Using Nonlinear Functions
• A Complex-Valued RTRL Algorithm for Recurrent Neural Networks
• Approximation by Fully Complex Multilayer Perceptrons
• Second-order analysis of improper complex random vectors and processes

This page was built for publication: Convergence analysis of an augmented algorithm for fully complex-valued neural networks