检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Liu, Zhiyu Han, Zhi Tang, Yandong Zhang, Hai Tang, Shaojie Wang, Yao State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Department of Statistics Northwest University Xi’an710000 China Department of Management Science and Systems State University of New York Buffalo United States Center for Intelligent Decision-making and Machine Learning School of Management Xi’an Jiaotong University Xi’an710049 China

We consider the noisy matrix sensing problem in the over-parameterization setting, where the estimated rank r is larger than the true rank r★. Specifically, our main objective is to recover a matrix X★ ∈ Rn1×n2 with rank r★ from noisy measurements using an over-parameterized factorized form LRT, where L ∈ n1×r, R ∈ n2×r and min{n1, n2} ≥ r > r★, with the true rank r★ being unknown. Recently, preconditioning methods have been proposed to accelerate the convergence of matrix sensing problem compared to vanilla gradient descent, incorporating preconditioning terms (LTL + λI)−1 and (RTR + λI)−1 into the original gradient. However, these methods require careful tuning of the damping parameter λ and are sensitive to initial points and step size. To address these limitations, we propose the alternating preconditioned gradient descent (APGD) algorithm, which alternately updates the two factor matrices, eliminating the need for the damping parameter and enabling faster convergence with larger step sizes. We theoretically prove that APGD achieves near-optimal error convergence at a linear rate, starting from arbitrary random initializations. Through extensive experiments, we validate our theoretical results and demonstrate that APGD outperforms other methods, achieving the fastest convergence rate. Notably, both our theoretical analysis and experimental results illustrate that APGD does not rely on the initialization procedure, making it more practical and versatile. Copyright © 2025, The Authors. All rights reserved.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

Wildlife Small Object Detection based on Enhanced Network in Ecological Surveillance 33

Wildlife Small Object Detection based on Enhanced Network in...

引用

第33届中国控制与决策会议

作者： Wan Dai Hongpeng Wang Yulin Song Yunwei Xin College of Computer Science Nankai University Tianjin Key Laboratory of Intelligent Robotics College of Artificial Intelligence Nankai University Research Laboratory of Machine Learning and Pervasive Computing Nankai University

ISBN: (纸本)9781665431293

Visual tele-observation is an effective way for intelligent monitoring and protection of ecology and the natural *** from pedestrian or rigid body detection,wildlife detection in natural scenes face more complex problems,such as the existence of wild background clutter,local or global vegetation occlusion of animals,small object,rotation,deformation,and other interfering *** this paper,We mainly propose a novel method for the small object *** our small object wild species data set,we use an SSD detector for object ***,the K-means algorithm is used to adjust the anchor box of the SSD ***,for the situation that SSD is not good for small object detection,in conv4 layers of SSD,the feature enhancement module is ***,aiming at the size of a small object,the network level of SSD is *** have proved the feasibility of each of the three methods through experiments and combined with the three methods to verify,the recognition rate of the small target has increased by 2.67%.

关键词： anchor feature enhancement hierarchical design wildlife detection

来源：评论

学校读者我要写书评

暂无评论

Source-level analysis of brain activity in the process of learning and retrieving new information 5

Source-level analysis of brain activity in the process of le...

引用

5th Scientific School on Dynamics of Complex Networks and their Applications, DCNA 2021

作者： Makarov, Vladimir Grubov, Vadim Kurkin, Semen Smirnov, Nikita Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia

ISBN: (纸本)9781665442824

In this paper, we discovered the increase in EEG power in the theta frequency range in the occipital cortex during a visual analysis of new information and the power decrease in the alpha range in the temporal lobe during retaining information. The revealed increase in theta power correlates with the response time and errors rate. The alpha power correlates with response time. Summarizing the above, the detected cluster of theta-activity during information perception may reflect the increased concentration of attention. © 2021 IEEE

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Quasi-movements as an intermediate type of motion 5

Quasi-movements as an intermediate type of motion

引用

5th Scientific School on Dynamics of Complex Networks and their Applications, DCNA 2021

作者： Smirnov, Nikita M. Kurkin, Semen Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia

ISBN: (纸本)9781665442824

This paper discusses the three distinct types of motor activity, namely quasi, real, and imagery. Quasi-motion is voluntary movements that are minimized to the point that finally become undetectable by objective measures. This type of motion is particular from the point of difficulty of classifying it as real or imaginary. In this paper, we are aiming to show it from the sensor- and source-level perspectives. © 2021 IEEE

关键词： Dynamics Complex networks

来源：评论

学校读者我要写书评

暂无评论

Biomarkers of brain activity for the performance evaluation in the process of solving cognitive tasks 5

Biomarkers of brain activity for the performance evaluation ...

引用

5th Scientific School on Dynamics of Complex Networks and their Applications, DCNA 2021

作者： Badarin, Artem Smirnov, Nikita Kurkin, Semen Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia

ISBN: (纸本)9781665442824

In this paper, we analyze the brain activity during the execution by the subject of simple cognitive tasks associated with visual attention and symbol perception. We obtain biomarkers of brain activity in the process of solving cognitive tasks. These biomarkers make it possible to relate the quality and speed of execution of the tasks offered to the subject with the brain’s activity of the cortical network. We use a combination of time-frequency and statistical analysis to calculate activity characteristics. The results obtained can be used to develop neural interfaces for training attention and adjusting the learning process. © 2021 IEEE

关键词： Biomarkers

来源：评论

学校读者我要写书评

暂无评论

Comparison on brain activity for mechanical imagery and execution: a brief review 5

Comparison on brain activity for mechanical imagery and exec...

引用

5th Scientific School on Dynamics of Complex Networks and their Applications, DCNA 2021

作者： Chepurova, Alla Kurkin, Semen Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia

ISBN: (纸本)9781665442824

With this review we summarize the current state of scientific studies in the field of MI (motor imagery) and ME (motor execution). We composed brain map and description which correlate different brain areas with type of movements it is responsible for. That gives a more complete and systematic picture of human brain functionality in a case of ME and MI. Also we found the research gap and possible improvements for the further researches in this field. © 2021 IEEE

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Intent-based Object Grasping by a Robot using Deep learning

Intent-based Object Grasping by a Robot using Deep Learning

引用

IEEE International Advance Computing Conference, IACC

作者： Faheem Hassan Zunjani Souvik Sen Himanshu Shekhar Aditya Powale Debadutta Godnaik G. C. Nandi Robotics and Machine Learning Laboratory Indian Institute of Information Technology Allahabad Allahabad India

ISBN: (纸本)9781538666791;9781538666784

A robot needs to predict an ideal rectangle for optimal object grasping based on the intent for that grasp. Mask Regional - Convolutional Neural Network (Detectron) can be used to generate the object mask and for object detection and a Convolutional Neural Network (CNN) can be used for ideal grasp rectangle prediction according to the supplied intent, as described in this paper. The masked image obtained from Detectron along with the metadata of the intent type has been fed to the Fully-Connected layers of the CNN which would generate the desired optimal rectangle for the specific intent and object. Before settling for a CNN for optimal rectangle prediction, conventional Neural Networks with different hidden layers have been tried and the accuracy achieved was low. A CNN has then been developed and tested with different layers and sizes of pool and strides to settle on the final CNN model that has been discussed here. The optimal predicted rectangle is then fed to a robot, ROS simulation of Baxter robot in this case, to perform the actual grasping of the object at the predicted location.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Entropy-based strategies for physical exploration of the environment's degrees of freedom

Entropy-based strategies for physical exploration of the env...

引用

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： Stefan Otte Johannes Kulick Marc Toussaint Oliver Brock Machine Learning and Robotics Lab Universität Stuttgart Germany Robotics and Biology Laboratory Technische Universität Berlin Germany

Physical exploration refers to the challenge of autonomously discovering and learning how to manipulate the environment's degrees of freedom (DOF)-by identifying promising points of interaction and pushing or pulling object parts to reveal DOF and their properties. Recent existing work focused on sub-problems like estimating DOF parameters from given data. Here, we address the integrated problem, focusing on the higher-level strategy to iteratively decide on the next exploration point before applying motion generation methods to execute the explorative action and data analysis methods to interpret the feedback. We propose to decide on exploration points based on the expected information gain, or change in entropy in the robot's current belief (uncertain knowledge) about the DOF. To this end, we first define how we represent such a belief. This requires dealing with the fact that the robot initially does not know which random variables (which DOF, and depending on their type, which DOF properties) actually exist. We then propose methods to estimate the expected information gain for an exploratory action. We analyze these strategies in simple environments and evaluate them in combination with full motion planning and data analysis in a physical simulation environment.

关键词： Joints Entropy Robots Random variables Trajectory Uncertainty Friction

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization of Wildlife Recognition with Distributed learning in Ecological Surveillance

Performance Optimization of Wildlife Recognition with Distri...

引用

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems

作者： Wan Dai Hongpeng Wang Yulin Song Yunwei Xin Tianjin Key Laboratory of Intelligent Robotics Tianjin Research Laboratory of Machine Learning and Pervasive Computing Nankai University Tianjin

ISBN: (数字)9781728107707

ISBN: (纸本)9781728107714

Recently, deep learning technology has been widely used in ecological environment monitoring, but there are still huge challenges in specific tasks. For example, data sets have increased over the past few years, and in a CPU environment, training is quite time consuming. In order to solve these problems, we bring up a novel and effective method to improve training speed. In this paper, we make use of multi-GPUs to achieve distributed parallel acceleration. Small and shallow networks are not suitable for distributed training, because the computation of each parameter in this network is much higher than that of multi-layer perception or automatic encoder architecture, we use convolutional neural network with parameter sharing as the training network. In this paper, the main adopted method is to compare the performance of training wildlife recognition in single GPU and multi-GPUs environments by using distributed deep learning framework TensorFlow. The experimental results show that multi-GPUs which adopt distributed architecture can significantly accelerate training time consumption than single GPU. The results of this experiment also provides strong support for our follow-up work.

关键词： Training Parallel processing Graphics processing units Distributed databases Computational modeling Data models Neural networks

来源：评论

学校读者我要写书评

暂无评论

Wireless personal training tracker for sports shooting 5

Wireless personal training tracker for sports shooting

引用

5th Scientific School on Dynamics of Complex Networks and their Applications, DCNA 2021

作者： Antipov, Vladimir Badarin, Artem Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Lobachevsky University Nizhny Novgorod Russia Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia

ISBN: (纸本)9781665442824

The article describes the process of developing a wireless software arrapat complex for measuring and logging various aspects of sports shooting training. The purpose of the development is to optimize and personalize the training process. This paper proposes an approach that allows synchronization up to 1 ms over a wireless network. As well as a method of writing a large amount of this on a microSD flash drive with minimal latency. © 2021 IEEE

关键词： Sports

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：