Quaternionic convolutional neural networks with trainable Bessel activation functions

DOI10.1007/S11785-023-01387-ZMaRDI QIDQ6175664zbMATH OpenOpenAlexFDO

Authors N. Vieira

Publication date 24 July 2023

Published in Complex Analysis and Operator Theory (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/s11785-023-01387-z

zbMATH Keywords

activation functionsartificial neural networks and deep learningBessel functionsparametric activation functionsquaternionic convolutional neural networks

Mathematics Subject Classification ID

Functions of hypercomplex variables and generalized variables (30G35) Bessel and Airy functions, cylinder functions, ({}_0F_1) (33C10) Applications of hypergeometric functions (33C90) Computational learning theory (68Q32) Artificial neural networks and deep learning (68T07)

Recommendations

• Bicomplex neural networks with hypergeometric activation functions
• Quaternion quantum neural network for classification
• Quaternion convolutional neural networks: current advances and future directions
• A survey on modern trainable activation functions
• SignReLU neural network and its approximation ability

Cites work

• A note on the complex and bicomplex valued neural networks
• Application of holomorphic functions in two and higher dimensions
• Bicomplex neural networks with hypergeometric activation functions
• Complex-valued neural networks with multi-valued neurons.
• scientific article; zbMATH DE number 3863589 (Why is no real title available?)
• scientific article; zbMATH DE number 48233 (Why is no real title available?)

Cited in

(3)

• Quaternion convolutional neural networks: current advances and future directions
• Finite-time synchronization of quaternion-valued neural networks with time-varying and proportional delay under hybrid sampled-data control with application to secure image encryption
• Synchronization of quaternion-valued inertial neural networks: a semi-Markov switching and hybrid control approach

This page was built for publication: Quaternionic convolutional neural networks with trainable Bessel activation functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6175664)