首页/论文/2011.08734

arXiv 2011.087342020-11-17cs.LG

Predicting Rigid Body Dynamics using Dual Quaternion Recurrent Neural Networks with Quaternion Attention

South Westfalia University of Applied Science（西南威斯特伐利亚应用科学大学）

Johannes Pöppelbaum, Andreas Schwung

发表信息：: Access-2022-18871
DOI：: 10.1109/ACCESS.2022.3196340

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

We propose a novel neural network architecture based on dual quaternions which allow for a compact representation of informations with a main focus on describing rigid body movements. To cover the dynamic behavior inherent to rigid body movements, we propose recurrent architectures in the neural network. To further model the interactions between individual rigid bodies as well as external inputs efficiently, we incorporate a novel attention mechanism employing dual quaternion algebra. The introduced architecture is trainable by means of gradient based algorithms. We apply our approach to a parcel prediction problem where a rigid body with an initial position, orientation, velocity and angular velocity moves through a fixed simulation environment which exhibits rich interactions between the parcel and the boundaries.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

结合实时循环学习与最大相关熵准则的四元数循环神经网络

Quaternion recurrent neural network with real-time recurrent learning and maximum correntropy criterion

Imperial College London（帝国理工学院）；Northeast Normal University（东北师范大学）

本文提出结合 RTRL 与 MCC 的鲁棒 QRNN，利用 GHR 微积分完成推导，并在肺癌放疗规则与不规则呼吸的内部标记运动预测中验证其抗异常值能力。

2024-04-03cs.LG

Quaternion-Valued Recurrent Projection Neural Networks on Unit Quaternions

University of Campinas（坎皮纳斯大学）

Hypercomplex-valued neural networks, including quaternion-valued neural networks, can treat multi-dimensional data as a single entity. In this paper, we present the quaternion-valued recurrent projection neural networks (QRPNNs). Briefly, QRPNNs are obtained by combining the non-local projection learning with the quaternion-valued recurrent correlation neural network (QRCNNs). We show that QRPNNs overcome the cross-talk problem of QRCNNs. Thus, they are appropriate to implement associative memories. Furthermore, computational experiments reveal that QRPNNs exhibit greater storage capacity and …

2020-01-30cs.LGcs.NEstat.ML

Quaternion Recurrent Neural Networks

Université d’Avignon（阿维尼翁大学）；Orkis（奥基斯公司）；MILA（米拉研究所）；Université de Montréal（蒙特利尔大学）；McGill University（麦吉尔大学）；Element AI（元素人工智能公司）

Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and long-term dependencies between the basic elements of a sequence. Nonetheless, popular tasks such as speech or images recognition, involve multi-dimensional input features that are characterized by strong internal dependencies between the dimensions of the input vector. We propose a novel quaternion recurrent neural network (QRNN), alongside with a quaternion long-short term memory neural network (QLSTM), that take into account both the external relations and these in…

2019-01-07cs.LGstat.ML

用于轴承故障诊断的多尺度四元数CNN与BiGRU及交叉自注意力特征融合

Multi-scale Quaternion CNN and BiGRU with Cross Self-attention Feature Fusion for Fault Diagnosis of Bearing

School of Computer Science and Technology, Guangdong University of Technology（广东工业大学计算机科学与技术学院）；Guangdong Mechanical and Electrical College（广东机电职业技术学院）；School of Artificial Intelligence, Shenzhen Polytechnic University（深圳职业技术大学人工智能学院）；Department of Computer Science, University of Macau（澳门大学计算机科学系）

本文提出一种结合多尺度四元数CNN、BiGRU与交叉自注意力特征融合的轴承故障诊断模型，有效提取多尺度隐藏特征并增强特征判别交互，在三个公开数据集上达到SOTA性能。

2024-05-25cs.AIcs.CVcs.LG

Bidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech Recognition

Université d'Avignon（阿维尼翁大学）；McGill University（麦吉尔大学）；Orkis（奥基斯）

Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long-short term memory (LSTM) recurrent neural networks have achieved state-of-the-art results in many speech recognition tasks, due to their efficient representation of long and short term dependencies in sequences of inter-dependent features. Nonetheless, internal dependencies within the element composing multidimensional features are weakly considered by traditional real-valued representations. We propose a novel quaternion long-short term memory (QLSTM) recurrent neural netw…

2018-11-06cs.LGcs.SDeess.AS

Quaternion Neural Networks for Multi-channel Distant Speech Recognition

University of Oxford（牛津大学）；Samsung AI（三星人工智能）；Avignon University（阿维尼翁大学）

Despite the significant progress in automatic speech recognition (ASR), distant ASR remains challenging due to noise and reverberation. A common approach to mitigate this issue consists of equipping the recording devices with multiple microphones that capture the acoustic scene from different perspectives. These multi-channel audio recordings contain specific internal relations between each signal. In this paper, we propose to capture these inter- and intra- structural dependencies with quaternion neural networks, which can jointly process multiple signals as whole quaternion entities. The qua…

2020-05-19cs.LGcs.SDeess.AS

更多相关论文收起更多论文

Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition

Université d'Avignon（阿维尼翁大学）；Université de Montréal（蒙特利尔大学）；McGill University（麦吉尔大学）；Orkis（奥基斯公司）；Element AI（Element AI公司）

Recently, the connectionist temporal classification (CTC) model coupled with recurrent (RNN) or convolutional neural networks (CNN), made it easier to train speech recognition systems in an end-to-end fashion. However in real-valued models, time frame components such as mel-filter-bank energies and the cepstral coefficients obtained from them, together with their first and second order derivatives, are processed as individual elements, while a natural alternative is to process such components as composed entities. We propose to group such elements in the form of quaternions and to process thes…

2018-06-20cs.LGcs.SDeess.AS

Hypercomplex-Valued Recurrent Correlation Neural Networks

Institute of Mathematics, Statistics, and Scientific Computing（数学、统计与科学计算研究所）；University of Campinas（坎皮纳斯大学）

Recurrent correlation neural networks (RCNNs), introduced by Chiueh and Goodman as an improved version of the bipolar correlation-based Hopfield neural network, can be used to implement high-capacity associative memories. In this paper, we extend the bipolar RCNNs for processing hypercomplex-valued data. Precisely, we present the mathematical background for a broad class of hypercomplex-valued RCNNs. Then, we provide the necessary conditions which ensure that a hypercomplex-valued RCNN always settles at an equilibrium using either synchronous or asynchronous update modes. Examples with bipolar…

2020-01-31cs.LGcs.NEstat.ML

用于采样分子晶体结构的刚体流

Rigid Body Flows for Sampling Molecular Crystal Structures

Microsoft Research AI4Science（微软研究院AI4Science）；Freie Universität Berlin（柏林自由大学）；Qualcomm AI Research, an initiative from Qualcomm Technologies, Inc.（高通AI研究院（高通技术公司旗下研究机构））；University of Amsterdam（阿姆斯特丹大学）；Rice University（莱斯大学）

提出面向晶体中分子位置与取向的刚体归一化流，利用单位四元数流及其双重覆盖性质建模旋转，并在四面体系统和 TIP4P ice XI 的玻尔兹曼生成器中验证。

2023-06-07cs.LGphysics.chem-phphysics.comp-ph

递归神经网络近似连续函数

Recurrent neural networks approximate continuous functions

本文证明，对于[-1,1]上的任意连续函数，存在一个固定权重和隐藏维度的ReLU递归神经网络，其时间演化可以均匀逼近该函数，并给出了收敛速率和极小极大下界。

2026-06-19cs.LGcs.SCmath.DS