检索结果-内蒙古大学图书馆

Multilayer perceptron ensembles in a truly sparse training context

Neural Computing and Applications 2025年

作者： van der Wal, Peter R. D. Strisciuglio, Nicola Azzopardi, George Mocanu, Decebal Constatin Information Systems Group Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Nijenborgh 9 Groningen9747 AG Netherlands Data Management and Biometrics Group Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Hallenweg 19 Enschede7522 NH Netherlands Department of Computer Science Faculty of Science Technology and Medicine University of Luxembourg Maison du Nombre 6 avenue de la Fonte Esch4364 Luxembourg

Ensemble learning for artificial neural networks (ANNs) is an effective method to enhance predictive performance. However, ANNs are computationally and memory intensive, and naively training multiple networks can lead to excessive training times and costs. An effective tool for improving ensemble efficiency is introducing topological sparsity. Even though several implementations of efficient ensembles have been proposed, none of them can provide actual benefits in terms of computational overhead as the sparsity is simulated using binary masks. In this paper, we address this issue by introducing a Truly Sparse Ensemble without binary masks and directly incorporate native sparsity. We also propose two algorithms for initializing new subnetworks within the ensemble, leveraging this native topological sparsity to enhance subnetwork diversity. We demonstrate the performance of the resulting models at high levels of sparsity on several datasets in terms of classification accuracy, floating point operations (FLOPs), and actual running time. The proposed methods outperform all baseline dense and truly sparse models on tabular data, successfully diversify the training trajectory of the subnetworks, and increase the topological distance between subnetworks after re-initialization. © The Author(s) 2025.

关键词： Digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

FlowTrack: Point-level Flow Network for 3D Single Object Tracking

FlowTrack: Point-level Flow Network for 3D Single Object Tra...

引用

IEEE/RSJ International Conference on intelligent Robots and systems (IROS)

作者： Shuo Li Yubo Cui Zhiheng Li Zheng Fang Faculty of Robot Science and Engineering Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Key Laboratory of Data Analytics and Optimization for Smart Industry Ministry of Education Northeastern University Shenyang China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

3D single object tracking (SOT) is a crucial task in fields of mobile robotics and autonomous driving. Traditional motion-based approaches achieve target tracking by estimating the relative movement of target between two consecutive frames. However, they usually overlook local motion information of the target and fail to exploit historical frame information effectively. To overcome the above limitations, we propose a point-level flow method with multi-frame information for 3D SOT task, called FlowTrack. Specifically, by estimating the flow for each point in the target, our method could capture the local motion details of target, thereby improving the tracking performance. Meanwhile, to handle scenes with sparse points, we present a learnable target feature as the bridge to efficiently integrate target information from past frames. Moreover, we design a Instance Flow Head to transform dense point-level flow into instance-level motion, effectively aggregating local motion information to obtain global target motion. Finally, our method achieves competitive performance with improvements of 5.9% on the KITTI and 2.9% on the NuScenes, compared to the next best method.

关键词： Bridges Target tracking Three-dimensional displays Aggregates Transforms Object tracking intelligent robots Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Generalized Laplace Approximation

arXiv

引用

arXiv 2024年

作者： Chen, Yinsong Yu, Samson S. Li, Zhong Lim, Chee Peng School of Engineering Deakin University MelbourneVIC3216 Australia Faculty of Mathmatics and Computer Science FernUniversität in Hagen Hagen58084 Germany Institute for Intelligent Systems Research Innovation Deakin University MelbourneVIC3216 Australia

In recent years, the inconsistency in Bayesian deep learning has garnered increasing attention. Tempered or generalized posterior distributions often offer a direct and effective solution to this issue. However, understanding the underlying causes and evaluating the effectiveness of generalized posteriors remain active areas of research. In this study, we introduce a unified theoretical framework to attribute Bayesian inconsistency to model misspecification and inadequate priors. We interpret the generalization of the posterior with a temperature factor as a correction for misspecified models through adjustments to the joint probability model, and the recalibration of priors by redistributing probability mass on models within the hypothesis space using data samples. Additionally, we highlight a distinctive feature of Laplace approximation, which ensures that the generalized normalizing constant can be treated as invariant, unlike the typical scenario in general Bayesian learning where this constant varies with model parameters post-generalization. Building on this insight, we propose the generalized Laplace approximation, which involves a simple adjustment to the computation of the Hessian matrix of the regularized loss function. This method offers a flexible and scalable framework for obtaining high-quality posterior distributions. We assess the performance and properties of the generalized Laplace approximation on state-of-the-art neural networks and real-world datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Joint Prediction of Traffic Spatial-Temporal data with Graph Sparse Attention Mechanism and Bidirectional Temporal Convolutional Network

SSRN

引用

SSRN 2024年

作者： Zhang, Dongran Yan, Jiangnan Polat, Kemal Alhudhaif, Adi Li, Jun Guangdong Provincial Key Laboratory of Intelligent Transportation System School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen518107 China Department of Electrical and Electronics Engineering Faculty of Engineering Bolu Abant Izzet Baysal University Bolu Turkey Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj11942 Saudi Arabia

Traffic flow prediction plays a crucial role in the management and operation of urban transportation systems. While extensive research has been conducted on predictions for individual transportation modes, there is relatively limited research on joint prediction across different transportation modes. Furthermore, existing multimodal traffic joint modeling methods often lack flexibility in spatial-temporal feature extraction. To address these issues, we propose a method called Graph Sparse Attention Mechanism with Bidirectional Temporal Convolutional Network (GSABT) for multimodal traffic spatial-temporal joint prediction. First, we use a multimodal graph multiplied by self-attention weights to capture spatial local features, and then employ the Top-U sparse attention mechanism to obtain spa-tial global features. Second, we utilize a bidirectional temporal convolutional network to enhance the temporal feature correlation between the output and input data, and extract inter-modal and intra-modal temporal features through the share-unique module. Finally, we have designed a multimodal joint prediction framework that can be flexibly extended to both spatial and temporal dimensions. Extensive experiments conducted on three real datasets indicate that the proposed model consistently achieves state-of-the-art predictive performance. © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

ASML-VDIO: Visual-Depth-Inertial Odometry using Selected Accurate and Stable Multi-Modal Landmarks in Structural Environments

ASML-VDIO: Visual-Depth-Inertial Odometry using Selected Acc...

引用

IEEE/RSJ International Conference on intelligent Robots and systems (IROS)

作者： Xingjian Luo Chenglin Pang Xuankang Wu Zheng Fang Faculty of Robot Science and Engineering Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Key Laboratory of Data Analytics and Optimization for Smart Industry Ministry of Education Northeastern University Shenyang China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In complex indoor structural scenes such as shopping centers and malls, camera pose estimation using pure point features is easy to fail due to the difficulty in extracting sufficient and stable point features from weak textures or dynamic environments. Recent works have attempted to address these challenges by introducing line features. However, the addition of line features increases the number of parameters and landmarks for BA (Bundle Adjustment), leading to efficiency reduction. This is a common issue in multi-modal SLAM (Simultaneous Localization And Mapping). To address this issue, this paper proposes a novel visual-depth-inertial odometry (ASML-VDIO) framework by combining RGB-D and IMU sensors. To improve the efficiency of BA, the proposed landmark classification method classifies 3D landmarks into accurate landmarks and other landmarks based on spatial consistency verification and depth range limitation. Then, accurate landmarks are fixed, and only other landmarks are optimized in the optimization of BA. Furthermore, to remove line features extracted from dynamic objects (pedestrian, shopping-car, etc), we propose a dynamic line removal method that combines geometric constraints and motion constraints of line features. Finally, the method is evaluated on public and author-collected datasets, showing competitive accuracy and robustness in complex indoor structural scenes while 71% speedup on optimization thread with same constraints.

关键词： Accuracy Simultaneous localization and mapping Dynamics Pose estimation Feature extraction Cameras Robustness Sensors Odometry Optimization

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Kidney Stone Segmentation Based on Segmentation Anything Model for Robotic-Assisted Endoscope Navigation 16th

Zero-Shot Kidney Stone Segmentation Based on Segmentation A...

引用

16th International Conference on intelligent Robotics and Applications, ICIRA 2023

作者： Meng, Hui Chen, Lingkai Zhu, Shiqiang Fei, Chentao Zhang, Yong Zheng, Miaojuan Han, Jianda Song, Wei School of Intelligent Science and Technology Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences 1 Sub-lane Xiangshan Hangzhou310024 China Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou311100 China Hangzhou ElephantChain Network Technology Co. Ltd. Hangzhou China Faculty of Mechanical Engineering and Automation Zhejiang Sci-Tech University Hangzhou310018 China College of Artificial Intelligence and Tianjin Key Laboratory of Intelligent Robotics Institute of Robotics and Automatic Information Systems Nankai University Tianjin300350 China

ISBN: (纸本)9789819964888

Biomedical robotics has had a significant impact on flexible ureteroscopy (FURS) for the management of nephrolithiasis. The biomedical robots provide a suitable and safe platform for FURS. However, operating the robots expertly still represents a challenge for surgeons. Vision-based navigation is an effective means to simplify the operations of robots by surgeons, which has great potential to improve surgical efficiency. To achieve vision-based navigation, the localization of kidney stones in endoscopic images is the first step. In this paper, we propose a stone segmentation method (SSM) based on zero-shot learning, which consists of segmentation anything model (SAM), an image preprocessing module, and a mask postprocessing module. The SAM segments all objects in endoscopic images, which lack semantic information. The preprocessing module is designed to suppress interference of reflective area in endoscopic images, and the mask postprocessing module is used to filter noise masks. The experimental results on our collected endoscopic images indicate that our method achieves close accuracy on stone segmentation compared with supervised U-Net and VGG_U-Net, which significantly outperforms the Ostu and the SAM. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Trans-Rotor: An Active Omnidirectional Aerial-Ground Vehicle With Differential Gear Joint Transformation Mechanism

Trans-Rotor: An Active Omnidirectional Aerial-Ground Vehicle...

引用

IEEE/RSJ International Conference on intelligent Robots and systems (IROS)

作者： Xuankang Wu Haoxiang Sun Tong Xiao Yanzhang Pan Zheng Fang Faculty of Robot Science and Engineering Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Key Laboratory of Data Analytics and Optimization for Smart Industry Ministry of Education Northeastern University Shenyang China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Aerial-ground vehicles have shown great potential in various fields due to their superior mobility and outstanding endurance. However, most of morphing aerial-ground vehicles consider little about controllability and traversability in ground mode. We present a novel aerial-ground vehicle called TransRotor. By proposing a differential gear joint, we equip TransRotor with omnidirectional mobility in both air and ground mode. Besides, using a four-wheel-steering model in ground mode provides better traversability and ground flexibility. Moreover, we design mid-mode transformation for Trans-Rotor, which provides smooth and rapid mode switching. In this work, we firstly propose a novel design of an aerial-ground vehicle. Then, we propose a decoupled controller considering the four-wheel-steer model to achieve autonomous navigation of the vehicle. Comprehensive experiments and a benchmark comparison are carried out to validate the outstanding performance of the proposed system, where the system shows ground flexibility and saves energy up to more than 95%.

关键词： Gears Switches Benchmark testing Controllability Hardware Kinetic theory Vehicle dynamics Servomotors intelligent robots Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

Discrete-time Layered-network Epidemics Model with Time-varying Transition Rates and Multiple Resources

arXiv

引用

arXiv 2022年

作者： Cui, Shaoxuan Liu, Fangzhou Jardón-Kojakhmetov, Hildeberto Cao, Ming Bernoulli Institute Faculty of Science and Engineering University of Groningen Netherlands Research Institute of Intelligent Control and Systems School of Astronautics Harbin Institute of Technology China ENTEG Faculty of Science and Engineering University of Groningen Netherlands

This paper studies a discrete-time time-varying multi-layer networked SIWS (susceptible-infected-water-susceptible) model with multiple resources under both single-virus and competing multi-virus settings. Besides the human-to-human interaction, we also consider that the disease can diffuse on different types of medium. We use resources to refer to any media through which the pathogen of a virus can spread, and do not restrict the resource only to be water. In the single-virus case, we give a full analysis of the system's behaviour related to its healthy state and endemic equilibrium. In the multi-virus case, we show analytically that different equilibria appear driven by the competition among all viruses. We also show that some analytical results of the time-invariant system can be expanded into time-varying cases. Finally, we illustrate the results through some *** Codes 93A15 37N25 92F05 © 2022, CC BY.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Structured learning of rigid-body dynamics: A survey and unified view from a robotics perspective

引用

GAMM Mitteilungen 2021年第2期44卷 e202100009-e202100009页

作者： Geist, A. René Trimpe, Sebastian Intelligent Control Systems Group Max Planck Institute for Intelligent Systems Stuttgart Germany Institute for Data Science in Mechanical Engineering RWTH Aachen University Aachen Germany

Accurate models of mechanical system dynamics are often critical for model-based control and reinforcement learning. Fully data-driven dynamics models promise to ease the process of modeling and analysis, but require considerable amounts of data for training and often do not generalize well to unseen parts of the state space. Combining data-driven modeling with prior analytical knowledge is an attractive alternative as the inclusion of structural knowledge into a regression model improves the model's data efficiency and physical integrity. In this article, we survey supervised regression models that combine rigid-body mechanics with data-driven modeling techniques. We analyze the different latent functions (such as kinetic energy or dissipative forces) and operators (such as differential operators and projection matrices) underlying common descriptions of rigid-body mechanics. Based on this analysis, we provide a unified view on the combination of data-driven regression models, such as neural networks and Gaussian processes, with analytical model priors. Furthermore, we review and discuss key techniques for designing structured models such as automatic differentiation. © 2021 The Authors. GAMM - Mitteilungen published by Wiley-VCH GmbH.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Models Predict Fatal Myocardial Infarction Within 10-years Followup Utilizing Explainable AI 23

Machine Learning Models Predict Fatal Myocardial Infarction ...

引用

23rd IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2023

作者： Tsarapatsani, Konstantina-Helen Sakellarios, Antonis Tsakanikas, Vasilis D. Kleber, Marcus Marz, Winfried Fotiadis, Dimitrios I. Biomedical Research Institute Foundation for Research and Technology-Hellas Ioannina Greece Medical Clinic V Mannheim Medical Faculty University of Heidelberg Mannheim Germany Mannheim Institute of Public Health Social and Preventive Medicine Medical Faculty Mannheim University of Heidelberg Mannheim Germany Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering University of Ioannina Biomedical Research Institute Foundation for Research and Technology-Hellas Ioannina Greece

ISBN: (纸本)9798350393118

Fatal myocardial infarction (MI) is one of the most common types of cardiovascular diseases that often presents in the emergency department. The prediction of death caused by myocardial infarction within 10-years follow-up is addressed in this study, using comorbidities, daily habits, clinical and laboratory data in binary and continuous data respectively. The used data are included in a cohort of the Ludwigshafen Risk and Cardiovascular Health (LURIC) study. The target feature, namely death caused by MI, contained 106 deceased patients and 2,321 alive patients in the final used dataset. The analysis was based on machine learning models (ML), such as support vector machine (SVM), light gradient-boosting machine (LGBM), Random Forest (RF), Decision Tree (DT). Their performance was estimated by Area Under Receiver Operating Characteristic Curve (AUC), Sensitivity, Specificity, Precision and Accuracy. Results show that LGBM was the most suitable of the aforementioned models to predict death caused by myocardial infarction within 10-years follow-up, achieving area under the curve (AUC) value equal to 77.03 %, accuracy 69.42 %, sensitivity 69.75 %, specificity 69.40% and precision 53.76 %. In addition, explainable artificial intelligence (xAI) was utilized and especially SHapley Additive exPlanations (SHAP) was the selected method. SHAP was utilized in order to shed light on the results, applying the LGBM model as the best predictive model. The provided SHAP plots contribute to the interpretation of how each independent feature aid to the final prediction. © 2023 IEEE.

关键词： Forecasting

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：