Quaternion convolutional neural networks: current advances and future directions

DOI10.1007/s00006-024-01350-xzbMATH Open1547.68679MaRDI QIDQ6603953

Carlos Gershenson, Gerardo Altamirano-Gómez

Publication date: 12 September 2024

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

zbMATH Keywords

quaternion algebradeep learningconvolutional neural network

Mathematics Subject Classification ID

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

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The quaternion domain Fourier transform and its properties
• Augmented second-order statistics of quaternion random signals
• Complex-valued neural networks
• Quaternion polar representation with a complex modulus and complex argument inspired by the Cayley-Dickson form.
• 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
• Quaternionic analyticity
• Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random field
• Regularisation of neural networks by enforcing Lipschitz continuity
• On quaternionic measures
• Clifford algebras and spinors.
• Hypercomplex Fourier Transforms of Color Images
• Calculus with a quaternionic variable
• On the history of the kronecker product
• Quaternionic analysis
• The octonions
• Fast Complexified Quaternion Fourier Transform
• The Theory of Quaternion Matrix Derivatives
• The Quaternion Calculus
• New Foundations in Mathematics
• Understanding Geometric Algebra
• Quaternion Fourier Transforms for Signal and Image Processing
• Properness and Widely Linear Processing of Quaternion Random Vectors
• Hypercomplex signals-a novel extension of the analytic signal to the multidimensional case
• The monogenic signal
• Efficient implementation of quaternion Fourier transform, convolution, and correlation by 2-D complex FFT
• Visual Feature Extraction by a Multilayered Network of Analog Threshold Elements
• Optimal Whitening and Decorrelation

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