Approximation by Fully Complex Multilayer Perceptrons

DOI10.1162/089976603321891846zbMath1085.68631OpenAlexW2164177859WikidataQ44894406 ScholiaQ44894406MaRDI QIDQ4816962

Taehwan Kim, Tülay Adali

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)

Related Items

Convergence analysis of an augmented algorithm for fully complex-valued neural networks, Fully complex conjugate gradient-based neural networks using Wirtinger calculus framework: deterministic convergence and its application, An augmented CRTRL for complex-valued recurrent neural networks, On Clifford neurons and Clifford multi-layer perceptrons, Non-fragile output-feedback synchronization for delayed discrete-time complex-valued neural networks with randomly occurring uncertainties, The universal approximation theorem for complex-valued neural networks, Computation and learning in high dimensions. Abstracts from the workshop held August 1--7, 2021 (hybrid meeting), Single-hidden-layer feed-forward quantum neural network based on Grover learning, Fixed points of complex-valued bidirectional associative memory, Complex-valued adaptive signal processing using nonlinear functions, A Complex-Valued RTRL Algorithm for Recurrent Neural Networks, Complex infomax: Convergence and approximation of infomax with complex nonlinearities, Multistability of complex-valued neural networks with discontinuous activation functions

Cites Work

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