English
Related papers

Related papers: Quaternion Backpropagation

200 papers

Many popular feature-attribution methods for interpreting deep neural networks rely on computing the gradients of a model's output with respect to its inputs. While these methods can indicate which input features may be important for the…

Machine Learning · Computer Science 2023-07-11 Kevin Du , Lucas Torroba Hennigen , Niklas Stoehr , Alexander Warstadt , Ryan Cotterell

Two aspects of neural networks that have been extensively studied in the recent literature are their function approximation properties and their training by gradient descent methods. The approximation problem seeks accurate approximations…

Machine Learning · Computer Science 2022-09-20 R. Gentile , G. Welper

This research note presents a derivation and implementation of efficient and scalable gradient computations using the celerite algorithm for Gaussian Process (GP) modeling. The algorithms are derived in a "reverse accumulation" or…

Instrumentation and Methods for Astrophysics · Physics 2018-02-01 Daniel Foreman-Mackey

This paper presents a graded hierarchy or chain of binary operations on the reals and the complex numbers. The operations are related distributively in the sense that any one of them distributes over the next lower operation in the chain.…

History and Overview · Mathematics 2007-05-23 Michael L. Carroll

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

Second order circularity, also called properness, for complex random variables is a well known and studied concept. In the case of quaternion random variables, some extensions have been proposed, leading to applications in quaternion signal…

General Mathematics · Mathematics 2016-11-24 Nicolas Le Bihan

For the first time, the development of the nonlinear geometrically exact governing equations and corresponding boundary conditions of hanging cantilevered flexible pipes conveying fluid in the framework of the quaternion system is…

Fluid Dynamics · Physics 2024-06-13 Amir Mehdi Dehrouyeh-Semnani

The attitude space has been parameterized in various ways for practical purposes. Different representations gain preferences over others based on their intuitive understanding, ease of implementation, formulaic simplicity, and physical as…

Systems and Control · Computer Science 2017-08-30 Hardik Parwana , Mangal Kothari

Given a set of observations generated by an optimization process, the goal of inverse optimization is to determine likely parameters of that process. We cast inverse optimization as a form of deep learning. Our method, called deep inverse…

Machine Learning · Computer Science 2018-12-04 Yingcong Tan , Andrew Delong , Daria Terekhov

In modern neural networks like Transformers, linear layers require significant memory to store activations during backward pass. This study proposes a memory reduction approach to perform backpropagation through linear layers. Since the…

Machine Learning · Computer Science 2022-02-04 Daniel Bershatsky , Aleksandr Mikhalev , Alexandr Katrutsa , Julia Gusak , Daniil Merkulov , Ivan Oseledets

Deep learning is a research hot topic in the field of machine learning. Real-value neural networks (Real NNs), especially deep real networks (DRNs), have been widely used in many research fields. In recent years, the deep complex networks…

Computer Vision and Pattern Recognition · Computer Science 2019-03-21 Jiasong Wu , Ling Xu , Youyong Kong , Lotfi Senhadji , Huazhong Shu

Recurrent neural networks (RNNs) are a class of neural networks used in sequential tasks. However, in general, RNNs have a large number of parameters and involve enormous computational costs by repeating the recurrent structures in many…

Machine Learning · Statistics 2024-03-25 Takashi Furuya , Kazuma Suetake , Koichi Taniguchi , Hiroyuki Kusumoto , Ryuji Saiin , Tomohiro Daimon

Neural Networks have been widely used to solve Partial Differential Equations. These methods require to approximate definite integrals using quadrature rules. Here, we illustrate via 1D numerical examples the quadrature problems that may…

Numerical Analysis · Mathematics 2022-03-09 Jon A. Rivera , Jamie M. Taylor , Ángel J. Omella , David Pardo

We show that the core reasons that complex and hypercomplex valued neural networks offer improvements over their real-valued counterparts is the weight sharing mechanism and treating multidimensional data as a single entity. Their algebra…

Neural and Evolutionary Computing · Computer Science 2020-09-10 Chase J Gaudet , Anthony S Maida

Despite being the cornerstone of deep learning, backpropagation is criticized for its inherent sequentiality, which can limit the scalability of very deep models. Such models faced convergence issues due to vanishing gradient, later…

Machine Learning · Computer Science 2025-04-01 Erwan Fagnou , Paul Caillon , Blaise Delattre , Alexandre Allauzen

Coded distributed computation has become common practice for performing gradient descent on large datasets to mitigate stragglers and other faults. This paper proposes a novel algorithm that encodes the partial derivatives themselves and…

Machine Learning · Computer Science 2022-06-22 Pedro Soto , Ilia Ilmer , Haibin Guan , Jun Li

We study matrix forms of quaternionic versions of the Fourier Transform and Convolution operations. Quaternions offer a powerful representation unit, however they are related to difficulties in their use that stem foremost from…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Giorgos Sfikas , George Retsinas

This paper presents two approaches to obtain the dynamical equations of mobile manipulators using dual quaternion algebra. The first one is based on a general recursive Newton-Euler formulation and uses twists and wrenches, which are…

Robotics · Computer Science 2022-10-04 Frederico F. A. Silva , Juan J. Quiroz-Omaña , Bruno V. Adorno

Let $\cO$ be a maximal order in a definite quaternion algebra over $\mathbb{Q}$ of prime discriminant $p$, and $\ell$ a small prime. We describe a probabilistic algorithm, which for a given left $O$-ideal, computes a representative in its…

Number Theory · Mathematics 2014-06-05 David Kohel , Kristin Lauter , Christophe Petit , Jean-Pierre Tignol

In this article a surprising result is demonstrated using the neural tangent kernel. This kernel is defined as the inner product of the vector of the gradient of an underlying model evaluated at training points. This kernel is used to…

Artificial Intelligence · Computer Science 2021-04-14 Matt Calder