Quaternion convolutional neural networks: current advances and future directions

DOI10.1007/S00006-024-01350-XMaRDI QIDQ6603953zbMATH OpenFDO

Authors Gerardo Altamirano-Gómez, Carlos Gershenson

Publication date 12 September 2024

Published in Advances in Applied Clifford Algebras (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

zbMATH Keywords

deep learningquaternion algebraconvolutional neural network

Mathematics Subject Classification ID

Research exposition (monographs, survey articles) pertaining to computer science (68-02) Artificial neural networks and deep learning (68T07) Functions of hypercomplex variables and generalized variables (30G35) Separable algebras (e.g., quaternion algebras, Azumaya algebras, etc.) (16H05)

Recommendations

• Quaternion-valued recurrent projection neural networks on unit quaternions
• scientific article; zbMATH DE number 2204113
• Quaternionic convolutional neural networks with trainable Bessel activation functions
• Quaternion quantum neurocomputing
• Convolutional neural networks in image understanding

Cites work

• scientific article; zbMATH DE number 1605815 (Why is no real title available?)
• scientific article; zbMATH DE number 43688 (Why is no real title available?)
• scientific article; zbMATH DE number 1028010 (Why is no real title available?)
• scientific article; zbMATH DE number 1987557 (Why is no real title available?)
• scientific article; zbMATH DE number 4118601 (Why is no real title available?)
• scientific article; zbMATH DE number 2204113 (Why is no real title available?)
• scientific article; zbMATH DE number 3208754 (Why is no real title available?)
• Augmented second-order statistics of quaternion random signals
• Calculus with a quaternionic variable
• Clifford algebras and spinors.
• Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random field
• Complex-valued neural networks
• Deep learning
• Efficient implementation of quaternion Fourier transform, convolution, and correlation by 2-D complex FFT
• Fast Complexified Quaternion Fourier Transform
• Hypercomplex Fourier Transforms of Color Images
• Hypercomplex signals-a novel extension of the analytic signal to the multidimensional case
• Neocognition: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
• Neural networks in multidimensional domains. Fundamentals and new trends in modelling and control
• New foundations in mathematics. The geometric concept of number
• On quaternionic measures
• On the history of the kronecker product
• Optimal Whitening and Decorrelation
• Properness and Widely Linear Processing of Quaternion Random Vectors
• Quaternion Fourier transforms for signal and image processing
• Quaternion polar representation with a complex modulus and complex argument inspired by the Cayley-Dickson form.
• Quaternionic analysis
• Quaternionic analyticity
• Regularisation of neural networks by enforcing Lipschitz continuity
• The Quaternion Calculus
• The Theory of Quaternion Matrix Derivatives
• The monogenic signal
• The octonions
• The quaternion domain Fourier transform and its properties
• Understanding geometric algebra. Hamilton, Grassmann, and Clifford for computer vision and graphics
• Visual Feature Extraction by a Multilayered Network of Analog Threshold Elements

Cited in

(1)

• Quaternionic convolutional neural networks with trainable Bessel activation functions

This page was built for publication: Quaternion convolutional neural networks: current advances and future directions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6603953)