Approximation by Fully Complex Multilayer Perceptrons

DOI10.1162/089976603321891846MaRDI QIDQ4816962zbMATH OpenOpenAlexWikidataFDO

Authors Taehwan Kim, Tülay Adalı

Publication date 14 September 2004

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/089976603321891846

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Fully complex multi-layer perceptron network for nonlinear signal processing
• scientific article; zbMATH DE number 1405266
• Functional multi-layer perceptron: A nonlinear tool for functional data analysis
• Lower bounds for approximation by MLP neural networks
• Multilayer feedforward networks are universal approximators

Cites work

• Approximation by superpositions of a sigmoidal function
• Complex domain backpropagation
• Fully complex multi-layer perceptron network for nonlinear signal processing
• Multilayer feedforward networks are universal approximators

Cited in

(21)

• The universal approximation theorem for complex-valued neural networks
• Generalized splitting 2D flexible activation function.
• Optimizing multilayer perceptrons to approximate nonlinear quaternion functions
• Convergence analysis of an augmented algorithm for fully complex-valued neural networks
• Non-fragile output-feedback synchronization for delayed discrete-time complex-valued neural networks with randomly occurring uncertainties
• A Complex-Valued RTRL Algorithm for Recurrent Neural Networks
• Physics-informed holomorphic neural networks (PIHNNs): solving 2D linear elasticity problems
• Multistability of complex-valued neural networks with discontinuous activation functions
• On Clifford neurons and Clifford multi-layer perceptrons
• scientific article; zbMATH DE number 17222 (Why is no real title available?)
• Complex-valued adaptive signal processing using nonlinear functions
• Bicomplex neural networks with hypergeometric activation functions
• Complex infomax: Convergence and approximation of infomax with complex nonlinearities
• Fully complex multi-layer perceptron network for nonlinear signal processing
• Complex-valued autoencoders
• Computation and learning in high dimensions. Abstracts from the workshop held August 1--7, 2021 (hybrid meeting)
• Fixed points of complex-valued bidirectional associative memory
• An augmented CRTRL for complex-valued recurrent neural networks
• On approximate learning by multi-layered feedforward circuits
• Single-hidden-layer feed-forward quantum neural network based on Grover learning
• Fully complex conjugate gradient-based neural networks using Wirtinger calculus framework: deterministic convergence and its application

This page was built for publication: Approximation by Fully Complex Multilayer Perceptrons

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4816962)