English
Related papers

Related papers: Hypercomplex Widely Linear Processing: Fundamental…

200 papers

Deep learning has enjoyed tremendous success in a variety of applications but its application to quantile regressions remains scarce. A major advantage of the deep learning approach is its flexibility to model complex data in a more…

Statistics Theory · Mathematics 2021-06-14 Qixian Zhong , Jane-Ling Wang

Recurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition. Some of the properties that make RNNs suitable for such tasks, for example robustness to…

Artificial Intelligence · Computer Science 2007-05-23 Alex Graves , Santiago Fernandez , Juergen Schmidhuber

A longstanding challenge for the Machine Learning community is the one of developing models that are capable of processing and learning from very long sequences of data. The outstanding results of Transformers-based networks (e.g., Large…

Machine Learning · Computer Science 2024-02-15 Matteo Tiezzi , Michele Casoni , Alessandro Betti , Tommaso Guidi , Marco Gori , Stefano Melacci

Graph Neural Networks (GNNs) have emerged as powerful tools for learning representations of graph-structured data. In addition to real-valued GNNs, quaternion GNNs also perform well on tasks on graph-structured data. With the aim of…

Machine Learning · Computer Science 2025-03-03 Rucha Bhalchandra Joshi , Sagar Prakash Barad , Nidhi Tiwari , Subhankar Mishra

Novel types of convolution operators for quaternion linear canonical transform (QLCT) are proposed. Type one and two are defined in the spatial and QLCT spectral domains, respectively. They are distinct in the quaternion space and are…

Classical Analysis and ODEs · Mathematics 2022-12-13 Xiaoxiao Hu , Dong Cheng , Kit Ian Kou

Lorentz's group represented by the hypercomplex system of numbers, which is based on dirac matrices, is investigated. This representation is similar to the space rotation representation by quaternions. This representation has several…

General Physics · Physics 2019-08-01 Konstantin Karplyuk , Oleksandr Zhmudskyy

The main properties of hypercomplex generalization of quaternion system as antiquaternion are presented in this article. Definitions and studied of antiquaternions conjugation are introduced, their norm and zero divisor, and how to perform…

Numerical Analysis · Computer Science 2014-06-16 Yakiv O. Kalinovsky , Dmitry V. Lande , Dr. Sc. , Yuliya E. Boyarinova , Alina S. Turenko

In recent years, a specific machine learning method called deep learning has gained huge attraction, as it has obtained astonishing results in broad applications such as pattern recognition, speech recognition, computer vision, and natural…

Machine Learning · Computer Science 2018-06-26 Seyed Sajad Mousavi , Michael Schukat , Enda Howley

Transformations in the field of computer graphics and geometry are one of the most important concepts for efficient manipulation and control of objects in 2-dimensional and 3-dimensional space. Transformations take many forms each with…

Computational Geometry · Computer Science 2023-03-24 Benjamin Kenwright

Bayesian models are a powerful tool for studying complex data, allowing the analyst to encode rich hierarchical dependencies and leverage prior information. Most importantly, they facilitate a complete characterization of uncertainty…

Machine Learning · Statistics 2023-04-25 Steven Winter , Trevor Campbell , Lizhen Lin , Sanvesh Srivastava , David B. Dunson

We review a lattice construction arising from quaternion algebras over number fields and use it to obtain some known extremal and densest lattices in dimensions 8 and 16. The benefit of using quaternion algebras over number fields is that…

Number Theory · Mathematics 2021-09-27 Laia Amorós , M. Taoufiq Damir , Camilla Hollanti

It is known that the quaternion algebras are central simple algebras and also clifford algebras. In this paper, we introduce a new class of quaternions called Lucas-Leonardo p-quaternions and derive several fundamental properties of these…

Combinatorics · Mathematics 2025-01-22 Diana Savin , Elif Tan

A general representation of the quaternion gradients presented in the literature is proposed, and an universal update equation for QLMS-like algorithms is obtained. The general update law is used to study the convergence of widely linear…

Optimization and Control · Mathematics 2014-10-13 Fernando G. Almeida Neto , Vítor H. Nascimento

We provide an algorithm that, given any order $O$ in a quaternion algebra over a global field, computes representatives of all right equivalence classes of right $O$-ideals, including the non-invertible ones. The theory is developed for a…

Number Theory · Mathematics 2025-02-28 Stefano Marseglia , Harry Smit

In the past decade, the field of quantum machine learning has drawn significant attention due to the prospect of bringing genuine computational advantages to now widespread algorithmic methods. However, not all domains of machine learning…

Many classes of images exhibit rotational symmetry. Convolutional neural networks are sometimes trained using data augmentation to exploit this, but they are still required to learn the rotation equivariance properties from the data.…

Machine Learning · Computer Science 2016-05-27 Sander Dieleman , Jeffrey De Fauw , Koray Kavukcuoglu

A novel single-frame quaternion estimator processing two vector observations is introduced. The singular cases are examined, and appropriate rotational solutions are provided. Additionally, an alternative method involving sequential…

Methodology · Statistics 2024-05-07 Caitong Peng , Daniel Choukroun

In this study, we introduce the concept of commutative quaternions and commutative quaternion matrices. Firstly, we give some properties of commutative quaternions and their Hamilton matrices. After that we investigate commutative…

Algebraic Geometry · Mathematics 2016-11-26 Hidayet Hüda Kösal , Murat Tosun

Recently, randomized algorithms for low-rank approximation of quaternion matrices have received increasing attention. However, for large-scale problems, existing quaternion orthonormalizations are inefficient, leading to slow rangefinders.…

Numerical Analysis · Mathematics 2024-06-19 Chao Chang , Yuning Yang

Machine learning techniques are used to predict theoretical constraints such as unitarity and boundedness from below in extensions of the Standard Model. This approach has proven effective for models incorporating additional SU(2) scalar…

High Energy Physics - Phenomenology · Physics 2025-12-19 Darius Jurčiukonis