检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Yufeng Zhang Jialu Pan Kenli Li Wanwei Liu Zhenbang Chen Xinwang Liu Ji Wang College of Computer Science and Electronic Engineering Hunan University Changsha China College of Computer Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology Changsha China College of Computer State Key Laboratory for High Performance Computing Key laboratory of Software Engineering for Complex Systems National University of Defense Technology Changsha China

Kullback-Leibler (KL) divergence is one of the most important measures to calculate the difference between probability distributions. In this paper, we theoretically study several properties of KL divergence between multivariate Gaussian distributions. Firstly, for any two n-dimensional Gaussian distributions Ɲ1 and Ɲ2, we prove that when KL(Ɲ2‖Ɲ1) ≤ ε (ε > 0) the supremum of KL (Ɲ1‖Ɲ2) is (1/2) ((-W0 (-e-(1+2ε)))-1 + log(-W0 (-e-(1+2ε))) - 1), where W0 is the principal branch of Lambert W function. For small ε, the supremum is ε + 2ε1.5 + O (ε2). This quantifies the approximate symmetry of small KL divergence between Gaussian distributions. We further derive the infimum of KL(Ɲ1‖Ɲ2) when KL(Ɲ2‖Ɲ1) ≥ M (M > 0). We give the conditions when the supremum and infimum can be attained. Secondly, for any three n-dimensional Gaussian distributions Ɲ1, Ɲ2, and Ɲ3, we theoretically show that an upper bound of KL (Ɲ1‖Ɲ3) is 3ε1 + 3ε2 + 2√ε1ε2 + o(ε1)+ o(ε2) when KL (Ɲ1‖Ɲ2) ≤ ε1 and KL(Ɲ2‖Ɲ3) ≤ ε2 (ε1, ε2 ≥ 0). This reveals that KL divergence between Gaussian distributions follows a relaxed triangle inequality. Note that, all these bounds in the theorems presented in this work are independent of the dimension n. Finally, we discuss several applications of our theories in deep learning, reinforcement learning, and sample complexity research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Recursive Composite Adaptive Controller for Robot Manipulators

引用

Space(Science & Technology) 2021年第1期2021卷 77-83页

作者： Jianfei Li Yaobing Wang Zhiyong Liu Xin Jing Chengwei Hu The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Beijing Key Laboratory of Intelligent Space Robotic System Technology and Applications Beijing Institute of Spacecraft System EngineeringBeijing 100094China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

In this paper,a new recursive implementation of composite adaptive control for robot manipulators is *** investigate the recursive composite adaptive algorithm and prove the stability directly based on the Newton-Euler equations in matrix form,which,to our knowledge,is the first result on this point in the *** proposed algorithm has an amount of computation O(n),which is less than any existing similar algorithms and can satisfy the computation need of the complicated multidegree *** manipulator of the Chinese Space Station is employed as a simulation example,and the results verify the effectiveness of this proposed recursive algorithm.

关键词： Robot manipulators robot

来源：评论

学校读者我要写书评

暂无评论

RNTrajRec: Road Network Enhanced Trajectory Recovery with Spatial-Temporal Transformer

RNTrajRec: Road Network Enhanced Trajectory Recovery with Sp...

引用

International Conference on Data Engineering

作者： Yuqi Chen Hanyuan Zhang Weiwei Sun Baihua Zheng School of Computer Science & Shanghai Key Laboratory of Data Science Fudan University Shanghai Institute of Intelligent Electronics & Systems School of Computing and Information Systems Singapore Management University

GPS trajectories are the essential foundations for many trajectory-based applications. Most applications require a large number of high sample rate trajectories to achieve a good performance. However, many real-life trajectories are collected with low sample rate due to energy concern or other constraints. We study the task of trajectory recovery in this paper as a means to increase the sample rate of low sample trajectories. Most existing works on trajectory recovery follow a sequence-to-sequence diagram, with an encoder to encode a trajectory and a decoder to recover real GPS points in the trajectory. However, these works ignore the topology of road network and only use grid information or raw GPS points as input. Therefore, the encoder model is not able to capture rich spatial information of the GPS points along the trajectory, making the prediction less accurate and less spatial consistent. In this paper, we propose a road network enhanced transformer-based framework, namely RNTrajRec, for trajectory recovery. RNTrajRec first uses a graph model, namely GridGNN, to learn the embedding features of each road segment. It next develops a spatial-temporal transformer model, namely GPSFormer, to learn rich spatial and temporal features along with a Sub-Graph Generation module to capture the spatial features for each GPS point in the trajectory. It finally forwards the outputs of encoder model to a multi-task decoder model to recover the missing GPS points. Extensive experiments based on three large-scale real-life trajectory datasets confirm the effectiveness of our approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamics Modeling with Realistic Constraints for Trajectory Tracking Control of Manipulator∗

Dynamics Modeling with Realistic Constraints for Trajectory ...

引用

2022 IEEE International Conference on Real-Time computing and Robotics, RCAR 2022

作者： Liu, Lu Zuo, Guoyu Li, Jiangeng Li, Jianfeng Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing100124 China Beijing University of Technology Faculty of Materials and Manufacturing Beijing100124 China Faculty of Materials and Manufacturing Beijing University of Technology Beijing100124 China

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

To meet the practical operation requirements of manipulators in industry, service and collaboration scenarios, trajectory tracking accuracy and system stability of manipulators are usually regarded as critical control objectives. This paper proposes a novel manipulator control method with three-level constraints, called the real deep Lagrangian network (Real-DeLaN). In this method, real data (also called physical data) are collected from the physical manipulator and utilized to train the Lagrangian dynamics network model to improve the migration ability from simulation to reality. The torque output of the dynamic model is corrected by the real-Time calculation of friction in the network. The contact force on the end effector of the manipulator is compensated based on the principle of virtual displacement work. The experimental results show that Real-DeLaN can better control the joints to perform trajectory tracking, reduce the friction error of the manipulator, and show better anti-interference ability. © 2022 IEEE.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Based Fuzzy Atmosfield in Human-robot Interaction

Multi-modal Based Fuzzy Atmosfield in Human-robot Interactio...

引用

第42届中国控制会议

作者： Xin-Heng Li Zhen-Tao Liu School of Automation China University of Geosciences(Wuhan) Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

Recently,the emotional robot has basic functions of perceiving and expressing emotions,but it still hard to communicate naturally between humans and *** major reason is that communication atmosphere is seldom considered in Human-robot Interaction(HRI).We propose Multi-modal(i.e.,music background,speech,and semantics) Based Fuzzy Atmosfield(FA),which can not only realize the dynamic adjustment of FA but also dynamically regulate human *** the experiment,a Pepper robot is used and one hundred volunteers are invited for HRI,and soothing piano pieces are used as background *** were filled by the volunteers after the experiments,from which the results show that 90% of the volunteers felt the dynamic changes in the communication atmosphere and 77% of the volunteers felt significant emotional regulation,which demonstrates the effectiveness of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Transferable Negative Prompts for Out-of-Distribution Detection

Learning Transferable Negative Prompts for Out-of-Distributi...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Tianqi Li Guansong Pang Xiao Bai Wenjun Miao Jin Zheng State Key Laboratory of Complex & Critical Software Environment School of Computer Science and Engineering Jiangxi Research Institute Beihang University China School of Computing and Information Systems Singapore Management University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead to mismatches between OOD images and In-Distribution (ID) categories, resulting in a high false positive rate. To address this issue, we introduce a novel OOD detection method, named ‘NegPrompt’, to learn a set of negative prompts, each representing a negative connotation of a given class label, for delineating the boundaries between ID and OOD images. It learns such negative prompts with ID data only, without any reliance on external out-lier data. Further, current methods assume the availability of samples of all ID classes, rendering them ineffective in open-vocabulary learning scenarios where the inference stage can contain novel ID classes not present during training. In contrast, our learned negative prompts are transferable to novel class labels. Experiments on various ImageNet benchmarks show that NegPrompt surpasses state-of-the-art prompt-learning-based OOD detection methods and maintains a consistent lead in hard OOD detection in closed- and open-vocabulary classification scenarios. Code is available at https://***/mala-lab/negprompt.

关键词： Training Learning systems Computer vision Codes Computational modeling Semantics Lead

来源：评论

学校读者我要写书评

暂无评论

Clustering single-cell RNA sequencing data by deep learning algorithm 9

Clustering single-cell RNA sequencing data by deep learning ...

引用

9th IEEE International Conference on Bioinformatics and Computational Biology, ICBCB 2021

作者： Bai, Litai Zhu, Yuan Yi, Ming Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Wuhan China

ISBN: (纸本)9780738132020

The development of single-cell RNA sequencing (scRNA-seq) technology provides a good opportunity to study cell heterogeneity and diversity. Especially, clustering is an important step in scRNA-seq analysis. With the advance of technology, many scRNA-seq data are available, which develop a lot of clustering methods. However, the existing methods usually employ the gene expression data, ignoring the related information between genes and the structure information in data. Therefore, we propose a new method (NDMgcn) to reconstruct the gene expression data based on the association of gene network, and cluster the data by Variational Autoencoder (V AE) and Graph Convolutional Network (GCN). The V AE learns low-dimensional information and the GCN learns structural information. The experimental results indicate that NDMgcn outperforms other popular algorithms in terms of NMI and ARI metrics. It provides a new insight for clustering scRNA-seq data from the network perspective. © 2021 IEEE.

关键词： RNA

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Algorithm for Underwater Environment Search 2

A Reinforcement Learning Algorithm for Underwater Environmen...

引用

2022 2nd International Conference on Artificial Intelligence, Big Data and Algorithms, CAIBDA 2022

作者： Xiong, Minglei Xie, Guangming State Key Laboratory for Turbulence and Complex Systems Intelligent Biomimetic Design Lab. College of Engineering Peking University Beijing100871 China Peng Cheng Laboratory Shenzhen518055 China Robot Technology Co. Ltd. Beijing100176 China

ISBN: (纸本)9783800760268

Known as an intelligent learning algorithm that can be employed without any sufficient prior information, the reinforcement learning algorithm has been widely used recently. The underwater unknown 3D environment search is a typical application scenario lacking any prior knowledge. This study proposes an algorithm framework including one agent and an intelligent swarm based on the idea of reinforcement learning. This learning algorithm can be adopted to train only one individual. Many of such individuals will then create an intelligent group which can efficiently and completely search underwater unknown 3D environments. Moreover, the proposed algorithm needs no further prior knowledge of the unknown environment. Even if the algorithm fails to reach the optimal level in the use of reinforcement learning, the results confirm the applicability prospect of reinforcement learning in this field and provide an appealing direction. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Experimental Design of Lower-limb Movement Recognition Based on Support Vector Machine 41

Experimental Design of Lower-limb Movement Recognition Based...

引用

第41届中国控制会议

作者： Wangyang Ge Juan Zhao Feng Wang Chi Xu Zhaohui Yang Jinhua She School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Department of Rehabilitation Union HospitalTongji Medical CollegeHuazhong Univ.Science & Technology School of Engineering Tokyo University of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

As a rehabilitation aid,the lower extremity rehabilitation robot usually works together with the patient during the rehabilitation training process,and achieves therapeutic effects by assisting the patient to complete movements within a certain trajectory for *** realize the active training of the rehabilitation robot,the rehabilitation robot needs to be able to recognize the patient's movement intention and cooperate with *** signals contain rich neuromuscular movement information and are often used to extract patients' movement *** this paper,using the principle of human lower extremity force generation,we designed an experiment for lower extremity action recognition of sEMG *** extracting the composition of feature vectors through time-domain feature values,we designed an SVM classifier to achieve the classification of five common lower extremity actions and obtained an average accuracy rate of 90.66% through the experiment,which verified the effectiveness of the experimental design.

关键词： sEMG signal SVM movement recognition lower-limb

来源：评论

学校读者我要写书评

暂无评论

Towards Pose Estimation for Large UAV in Close Range

Towards Pose Estimation for Large UAV in Close Range

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Ni Ou Junzheng Wang Shangfei Liu Jiehao Li State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing China

ISBN: (纸本)9781665465373

This paper deals with the problem of 4D pose estimation for large unmanned aerial vehicles (UAVs) in close range. A sensor system consisting of one single point laser range-finder and two cameras is designed and a novel pose estimation method based on vision fusion and point cloud registration is proposed. Our approach works on one-shot mode and only requires 10 samples with real poses for template construction. Through V-rep simulation environment, we generate two 200-sample datasets of different difficulty for evaluation. Error quantiles, 5cm5deg and 10cml0deg are three evaluation metrics used in our ablation experiments. It is illustrated that our method outperforms in robustness and precision due to proposed dimension extension modification and fusion of vision sensors.

关键词： Point cloud compression Measurement Cloud computing Pose estimation Vision sensors Autonomous aerial vehicles Laser modes

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：