A survey of quaternion neural networks

T Parcollet, M Morchid, G Linares - Artificial Intelligence Review, 2020 - Springer
Quaternion neural networks have recently received an increasing interest due to noticeable
improvements over real-valued neural networks on real world tasks such as image, speech …

Quaternion convolutional long short-term memory neural model with an adaptive decomposition method for wind speed forecasting: North aegean islands case …

M Neshat, MM Nezhad, S Mirjalili, G Piras… - Energy Conversion and …, 2022 - Elsevier
An accurate prediction of short-term and long-term wind speed is necessary in order to
integrate wind energy into large-scale grid power. However, wind speed presents diverse …

A journey from improper Gaussian signaling to asymmetric signaling

S Javed, O Amin, B Shihada… - … Surveys & Tutorials, 2020 - ieeexplore.ieee.org
The deviation of continuous and discrete complex random variables from the traditional
proper and symmetric assumption to a generalized improper and asymmetric …

Augmented second-order statistics of quaternion random signals

CC Took, DP Mandic - Signal Processing, 2011 - Elsevier
Second order statistics of quaternion random variables and signals are revisited in order to
exploit the complete second order statistical information available. The conditions for Q …

A comprehensive review on the advancement of high-dimensional neural networks in quaternionic domain with relevant applications

S Kumar, U Rastogi - Archives of Computational Methods in Engineering, 2023 - Springer
The neurocomputing communities have focused much interest on quaternionic-valued
neural networks (QVNNs) due to the natural extension in quaternionic signals, learning of …

Optimization in quaternion dynamic systems: Gradient, hessian, and learning algorithms

D Xu, Y **a, DP Mandic - IEEE transactions on neural networks …, 2015 - ieeexplore.ieee.org
The optimization of real scalar functions of quaternion variables, such as the mean square
error or array output power, underpins many practical applications. Solutions typically …

Enabling quaternion derivatives: The generalized HR calculus

D Xu, C Jahanchahi, CC Took… - Royal Society open …, 2015 - royalsocietypublishing.org
Quaternion derivatives exist only for a very restricted class of analytic (regular) functions;
however, in many applications, functions of interest are real-valued and hence not analytic …

The theory of quaternion matrix derivatives

D Xu, DP Mandic - IEEE Transactions on Signal Processing, 2015 - ieeexplore.ieee.org
A systematic framework for the calculation of the derivatives of quaternion matrix functions
with respect to quaternion matrix variables is introduced. The proposed approach is …

A class of quaternion Kalman filters

C Jahanchahi, DP Mandic - IEEE Transactions on Neural …, 2013 - ieeexplore.ieee.org
The existing Kalman filters for quaternion-valued signals do not operate fully in the
quaternion domain, and are combined with the real Kalman filter to enable the tracking in 3 …

Fixed-time and prescribed-time synchronization of quaternion-valued neural networks: A control strategy involving Lyapunov functions

T Peng, Y Wu, Z Tu, AS Alofi, J Lu - Neural Networks, 2023 - Elsevier
A control strategy containing Lyapunov functions is proposed in this paper. Based on this
strategy, the fixed-time synchronization of a time-delay quaternion-valued neural network …