English
Related papers

Related papers: Geometric Clifford Algebra Networks

200 papers

This paper explores the representation of quantum computing in terms of unitary reflections (unitary transformations that leave invariant a hyperplane of a vector space). The symmetries of qubit systems are found to be supported by…

Quantum Physics · Physics 2010-08-23 Michel Planat , Maurice R. Kibler

Graph convolutional neural networks (GCNNs) have been attracting increasing research attention due to its great potential in inference over graph structures. However, insufficient effort has been devoted to the aggregation methods between…

Machine Learning · Computer Science 2019-05-15 Penghui Sun , Jingwei Qu , Xiaoqing Lyu , Haibin Ling , Zhi Tang

In this article, we develop an algebraic framework of axioms which abstracts various high-level properties of multi-qudit representations of generalized Clifford algebras. We further construct an explicit model and prove that it satisfies…

Quantum Physics · Physics 2022-08-23 Robert Lin

We present GEOPARD, a transformer-based architecture for predicting articulation from a single static snapshot of a 3D shape. The key idea of our method is a pretraining strategy that allows our transformer to learn plausible candidate…

Computer-aided molecular design (CAMD) studies quantitative structure-property relationships and discovers desired molecules using optimization algorithms. With the emergence of machine learning models, CAMD score functions may be replaced…

Computational Engineering, Finance, and Science · Computer Science 2023-12-07 Shiqiang Zhang , Juan S. Campos , Christian Feldmann , Frederik Sandfort , Miriam Mathea , Ruth Misener

Some connections between quadratic forms over the field of two elements, Clifford algebras of quadratic forms over the real numbers, real graded division algebras, and twisted group algebras will be highlighted. This allows to revisit real…

Rings and Algebras · Mathematics 2020-02-28 Alberto Elduque , Adrián Rodrigo-Escudero

Graph Convolutional Networks (GCNs) have recently become the primary choice for learning from graph-structured data, superseding hash fingerprints in representing chemical compounds. However, GCNs lack the ability to take into account the…

Machine Learning · Computer Science 2020-07-03 Tomasz Danel , Przemysław Spurek , Jacek Tabor , Marek Śmieja , Łukasz Struski , Agnieszka Słowik , Łukasz Maziarka

In this paper we start from a basic notion of process, which we structure into two groupoids, one orthogonal and one symplectic. By introducing additional structure, we convert these groupoids into orthogonal and symplectic Clifford…

Quantum Physics · Physics 2012-11-12 B. J. Hiley

Quantum general relativity may be considered as generally covariant QFT on differentiable manifolds, without any a priori metric structure. The kinematically covariance group acts by general diffeomorphisms on the manifold and by…

General Relativity and Quantum Cosmology · Physics 2007-05-23 M. Rainer

We present a PDE-based framework that generalizes Group equivariant Convolutional Neural Networks (G-CNNs). In this framework, a network layer is seen as a set of PDE-solvers where geometrically meaningful PDE-coefficients become the…

Machine Learning · Computer Science 2022-08-24 Bart Smets , Jim Portegies , Erik Bekkers , Remco Duits

Geometric Deep Learning techniques have become a transformative force in the field of Computer-Aided Design (CAD), and have the potential to revolutionize how designers and engineers approach and enhance the design process. By harnessing…

Computational Geometry · Computer Science 2025-07-08 Negar Heidari , Alexandros Iosifidis

This paper unifies the concept of kinematic mappings by using geometric algebras. We present a method for constructing kinematic mappings for certain Cayley-Klein geometries. These geometries are described in an algebraic setting by the…

Metric Geometry · Mathematics 2013-11-04 Daniel Klawitter , Markus Hagemann

We propose two graph neural network layers for graphs with features in a Riemannian manifold. First, based on a manifold-valued graph diffusion equation, we construct a diffusion layer that can be applied to an arbitrary number of nodes and…

Machine Learning · Computer Science 2025-02-26 Martin Hanik , Gabriele Steidl , Christoph von Tycowicz

Let $V$ be a $n$-dimensional real vector space. In this paper we introduce the concept of \emph{euclidean} Clifford algebra $\mathcal{C\ell}(V,G_{E})$ for a given euclidean structure on $V,$ i.e., a pair $(V,G_{E})$ where $G_{E}$ is a…

Mathematical Physics · Physics 2016-08-16 V. V. Fernández , A. M. Moya , W. A. Rodrigues

Deep convolutional networks have become the mainstream in computer vision applications. Although CNNs have been successful in many computer vision tasks, it is not free from drawbacks. The performance of CNN is dramatically degraded by…

Computer Vision and Pattern Recognition · Computer Science 2021-07-23 Takashi Shibata , Masayuki Tanaka , Masatoshi Okutomi

Many scientific fields study data with an underlying structure that is a non-Euclidean space. Some examples include social networks in computational social sciences, sensor networks in communications, functional networks in brain imaging,…

Computer Vision and Pattern Recognition · Computer Science 2017-08-02 Michael M. Bronstein , Joan Bruna , Yann LeCun , Arthur Szlam , Pierre Vandergheynst

Medical image segmentation demands models that achieve high accuracy while maintaining computational efficiency and clinical interpretability. While recent Kolmogorov-Arnold Networks (KANs) offer powerful adaptive non-linearities, their…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Guojie Li , Tianyi Liu , Anwar P. P. Abdul Majeed , Muhammad Ateeq , Anh Nguyen , Fan Zhang

The Euclidean scattering transform was introduced nearly a decade ago to improve the mathematical understanding of convolutional neural networks. Inspired by recent interest in geometric deep learning, which aims to generalize convolutional…

Machine Learning · Statistics 2023-07-26 Michael Perlmutter , Feng Gao , Guy Wolf , Matthew Hirn

Attention mechanisms are developing into a viable alternative to convolutional layers as elementary building block of NNs. Their main advantage is that they are not restricted to capture local dependencies in the input, but can draw…

Machine Learning · Computer Science 2021-09-07 Thorben Frank , Stefan Chmiela

Group convolutional neural networks (G-CNNs) can be used to improve classical CNNs by equipping them with the geometric structure of groups. Central in the success of G-CNNs is the lifting of feature maps to higher dimensional disentangled…

Machine Learning · Computer Science 2021-03-23 Erik J Bekkers