中文
相关论文

相关论文: Lie Neurons: Adjoint-Equivariant Neural Networks f…

200 篇论文

Many scientific and geometric problems exhibit general linear symmetries, yet most equivariant neural networks are built for compact groups or simple vector features, limiting their reuse on matrix-valued data such as covariances, inertias,…

机器学习 · 计算机科学 2026-02-02 Chankyo Kim , Sicheng Zhao , Minghan Zhu , Tzu-Yuan Lin , Maani Ghaffari

Recent work has constructed neural networks that are equivariant to continuous symmetry groups such as 2D and 3D rotations. This is accomplished using explicit Lie group representations to derive the equivariant kernels and nonlinearities.…

机器学习 · 计算机科学 2022-12-08 Noah Shutty , Casimir Wierzynski

We introduce the concept of a semigroup coupled cell network and show that the collection of semigroup network vector fields forms a Lie algebra. This implies that near a dynamical equilibrium the local normal form of a semigroup network is…

动力系统 · 数学 2012-09-17 Bob Rink , Jan Sanders

Group equivariant neural networks are used as building blocks of group invariant neural networks, which have been shown to improve generalisation performance and data efficiency through principled parameter sharing. Such works have mostly…

机器学习 · 计算机科学 2021-06-17 Michael Hutchinson , Charline Le Lan , Sheheryar Zaidi , Emilien Dupont , Yee Whye Teh , Hyunjik Kim

Invariance and equivariance to the rotation group have been widely discussed in the 3D deep learning community for pointclouds. Yet most proposed methods either use complex mathematical tools that may limit their accessibility, or are tied…

计算机视觉与模式识别 · 计算机科学 2021-04-27 Congyue Deng , Or Litany , Yueqi Duan , Adrien Poulenard , Andrea Tagliasacchi , Leonidas Guibas

The translation equivariance of convolutional layers enables convolutional neural networks to generalize well on image problems. While translation equivariance provides a powerful inductive bias for images, we often additionally desire…

机器学习 · 统计学 2020-09-25 Marc Finzi , Samuel Stanton , Pavel Izmailov , Andrew Gordon Wilson

Invariance and equivariance to geometrical transformations have proven to be very useful inductive biases when training (convolutional) neural network models, especially in the low-data regime. Much work has focused on the case where the…

机器学习 · 计算机科学 2024-07-11 Mircea Mironenco , Patrick Forré

We propose Lie group embedded dynamical neural networks (LieEDNN) and the corresponding learning algorithms based on gradient descent and metric projection on smooth manifold, where we treat Lie group as an intrinsic representation for…

机器学习 · 计算机科学 2026-05-27 Tianwei Wang , Bryan Chen , Qian Zuo , Qiyue Xia , Xin Li , Wei Pang

Equivariant neural networks are neural networks with symmetry. Motivated by the theory of group representations, we decompose the layers of an equivariant neural network into simple representations. The nonlinear activation functions lead…

机器学习 · 计算机科学 2026-03-30 Joel Gibson , Daniel Tubbenhauer , Geordie Williamson

Reductive Lie Groups, such as the orthogonal groups, the Lorentz group, or the unitary groups, play essential roles across scientific fields as diverse as high energy physics, quantum mechanics, quantum chromodynamics, molecular dynamics,…

机器学习 · 统计学 2023-06-02 Ilyes Batatia , Mario Geiger , Jose Munoz , Tess Smidt , Lior Silberman , Christoph Ortner

Equivariance of linear neural network layers is well studied. In this work, we relax the equivariance condition to only be true in a projective sense. We propose a way to construct a projectively equivariant neural network through building…

计算机视觉与模式识别 · 计算机科学 2023-12-21 Georg Bökman , Axel Flinth , Fredrik Kahl

Equivariance of neural networks to transformations helps to improve their performance and reduce generalization error in computer vision tasks, as they apply to datasets presenting symmetries (e.g. scalings, rotations, translations). The…

计算机视觉与模式识别 · 计算机科学 2022-11-08 Mateus Sangalli , Samy Blusseau , Santiago Velasco-Forero , Jesus Angulo

In the computation of the normal form of a colored network vector field, following the semigroup(oid) approach in [19], one would like to be able to say something about the structure of the Lie algebra of linear colored network vector…

动力系统 · 数学 2024-09-24 Fahimeh Mokhtari , Jan Sanders

We survey the mathematical foundations of geometric deep learning, focusing on group equivariant and gauge equivariant neural networks. We develop gauge equivariant convolutional neural networks on arbitrary manifolds $\mathcal{M}$ using…

In recent years, deep learning techniques have shown great success in various tasks related to inverse problems, where a target quantity of interest can only be observed through indirect measurements by a forward operator. Common approaches…

数值分析 · 数学 2024-03-18 Matthias Beckmann , Nick Heilenkötter

We present the group equivariant conditional neural process (EquivCNP), a meta-learning method with permutation invariance in a data set as in conventional conditional neural processes (CNPs), and it also has transformation equivariance in…

机器学习 · 计算机科学 2021-02-18 Makoto Kawano , Wataru Kumagai , Akiyoshi Sannai , Yusuke Iwasawa , Yutaka Matsuo

In this paper, we develop a manifestly geometric framework for equivariant manifold neural ordinary differential equations (NODEs) and use it to analyse their modelling capabilities for symmetric data. First, we consider the action of a Lie…

机器学习 · 计算机科学 2024-10-11 Emma Andersdotter , Daniel Persson , Fredrik Ohlsson

Equivariant neural networks incorporate symmetries through group actions, embedding them as an inductive bias to improve performance. Existing methods learn an equivariant action on the latent space, or design architectures that are…

机器学习 · 计算机科学 2026-05-19 Riccardo Ali , Pietro Liò , Jamie Vicary

In recent years, skeleton-based action recognition has become a popular 3D classification problem. State-of-the-art methods typically first represent each motion sequence as a high-dimensional trajectory on a Lie group with an additional…

计算机视觉与模式识别 · 计算机科学 2017-04-12 Zhiwu Huang , Chengde Wan , Thomas Probst , Luc Van Gool

Quantum neural network architectures that have little-to-no inductive biases are known to face trainability and generalization issues. Inspired by a similar problem, recent breakthroughs in machine learning address this challenge by…

‹ 上一页 1 2 3 10 下一页 ›