检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jacob Sacks Rwik Rana Kevin Huang Alex Spitzer Guanya Shi Byron Boots University of Washington Seattle WA USA Robotics Institute Carnegie Mellon University Pittsburgh PA USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

A major challenge in robotics is to design robust policies which enable complex and agile behaviors in the real world. On one end of the spectrum, we have model-free reinforcement learning (MFRL), which is incredibly flexible and general but often results in brittle policies. In contrast, model predictive control (MPC) continually re-plans at each time step to remain robust to perturbations and model inaccuracies. However, despite its real-world successes, MPC often under-performs the optimal strategy. This is due to model quality, myopic behavior from short planning horizons, and approximations due to computational constraints. And even with a perfect model and enough compute, MPC can get stuck in bad local optima, depending heavily on the quality of the optimization algorithm. To this end, we propose Deep Model Predictive Optimization (DMPO), which learns the inner-loop of an MPC optimization algorithm directly via experience, specifically tailored to the needs of the control problem. We evaluate DMPO on a real quadrotor agile trajectory tracking task, on which it improves performance over a baseline MPC algorithm for a given computational budget. It can outperform the best MPC algorithm by up to 27% with fewer samples and an end-to-end policy trained with MFRL by 19%. Moreover, because DMPO requires fewer samples, it can also achieve these benefits with 4.3× less memory. When we subject the quadrotor to turbulent wind fields with an attached drag plate, DMPO can adapt zero-shot while still outperforming all baselines. Additional results can be found at https://***/mr2ywmnw.

关键词： Runtime Trajectory tracking Computational modeling Predictive models Prediction algorithms approximation algorithms Trajectory

来源：评论

学校读者我要写书评

暂无评论

FocusCore Decomposition of Multilayer Graphs

FocusCore Decomposition of Multilayer Graphs

引用

International Conference on Data Engineering

作者： Run-An Wang Dandan Liu Zhaonian Zou Harbin Institute of Technology China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Mining dense subgraphs on multilayer graphs offers the opportunity for more in-depth discoveries than classical dense subgraph mining on single-layer graphs. However, the existing approaches fail to ensure the denseness of a discovered subgraph on layers of users' interest and simultaneously gain partial supports on the denseness from other layers. In this paper, we introduce a novel dense subgraph model called FocusCore (FoCore) for multilayer graphs, which can pay more attention to layers focused on by users. The FoCore decomposition problem, i.e., identifying all nonempty FoCores in a multilayer graph, can be addressed by executing the peeling process with respect to all possible configurations of focus and background layers. By utilizing the nice properties of FoCores, we devise an interleaved peeling algorithm and a vertex-centric algorithm towards efficient FoCore decomposition. As an application, we propose a FoCore-decomposition-based algorithm to approximate the densest subgraph in a multilayer graph with a provable approximation guarantee. The extensive experiments on real-world datasets verify the effectiveness of the FoCore model and the efficiency of the proposed algorithms.

关键词： Nonhomogeneous media approximation algorithms Data engineering

来源：评论

学校读者我要写书评

暂无评论

Vegetable Disease Identification Algorithm Based on Improved Swin Transformer

Vegetable Disease Identification Algorithm Based on Improved...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Fahai Wang Yiqun Wang Mengchen Liu Wenbai Chen Yichen Wang Yanzhuo Xi College of Automation Beijing Information Science and Technology University Beijing China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

The background of vegetable disease images is complex, with the diseased areas exhibiting minimal contrast against the backdrop, making the precise identification of foliar diseases in vegetables a significant challenge in agricultural production. This study aims to address the insufficiencies in recognition accuracy inherent to traditional identification models by implementing enhancements based on the Swin Transformer model. The paper proposes the design of a local perception module that, by expanding the size of the perceptual field, enhances the capability for local feature extraction to optimize model recognition accuracy. Additionally, the Poly Loss function is employed to address the issue of data imbalance within the vegetable disease dataset. Experimental results indicate that the model proposed herein consistently outperforms other recognition models in comparative assessments, achieving an accuracy rate of 97.14%, which represents an approximate 3.6% improvement over the baseline model. The model holds promising prospects for application in identifying foliar diseases of vegetables.

关键词： Smart agriculture Measurement Accuracy Production Transformers Feature extraction approximation algorithms Artificial intelligence Diseases

来源：评论

学校读者我要写书评

暂无评论

Eliminating Majority Illusion 25

Eliminating Majority Illusion

引用

Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems

作者： Foivos Fioravantes Abhiruk Lahiri Antonio Lauerbach Lluís Sabater Marie Diana Sieper Samuel Wolf Czech Technical University of Prague Prague Czech Rep Heinrich Heine University Dusseldorf Germany Julius-Maximilians-University Wurzburg Germany Charles University Prague Czech Rep

ISBN: (纸本)9798400714269

An opinion illusion refers to a phenomenon in social networks where agents may witness distributions of opinions among their neighbours that do not accurately reflect the true distribution of opinions in the population as a whole. A specific case of this occurs when there are only two possible choices, such as whether to receive the COVID-19 vaccine or vote on EU membership, which is commonly referred to as a majority illusion. In this work, we study the topological properties of social networks that lead to opinion illusions and focus on minimizing the number of agents that need to be influenced to eliminate these illusions. To do so, we propose an initial, but systematic study of the algorithmic behaviour of this *** show that the problem is NP-hard even for underlying topologies that are rather restrictive, being planar and of bounded diameter. We then look for exact algorithms that scale well as the input grows (FPT). We argue the in-existence of such algorithms even when the number of vertices that must be influenced is bounded, or when the social network is arranged in a ''path-like'' fashion (has bounded pathwidth). On the positive side, we present an FPT algorithm for networks with a ''star-like'' structure (bounded vertex cover number). Finally, we construct an FPT algorithm for ''tree-like'' networks (bounded treewidth) when the number of vertices that must be influenced is bounded. This algorithm is then used to provide a PTAS for planar graphs.

关键词： approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Near-Field Tracking for Reconfigurable Intelligent Surface Aided Systems Harnessing the NLoS Paths

Near-Field Tracking for Reconfigurable Intelligent Surface A...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Lingzhi Xia Rui Wang Xiaojun Yuan Boyu Teng José Rodríguez-Piñeiro College of Electronics and Information Engineering Tongji University Shanghai China National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9788831299107

ISBN: (纸本)9798350366327

In this paper, the near-field tracking problem harnessing the non-line-of-sight (NLoS) paths is investigated for reconfigurable intelligent surface (RIS)-aided systems. In order to reduce the complexity of the position estimation, the near-field signal model, where the virtual line-of-sight (VLoS) paths and NLoS paths coexist, is constructed by employing the subarray far-field model. A probability transition model for the tracking problem is established, as well as the corresponding factor graph. Then, a low complexity near-field tracking algorithm based on message passing is developed to jointly estimate the UE's and scatterers' positions in each time slot. Numerical results show that the mean square error (MSE) of the proposed algorithm performs close to the misspecified Cramér-Rao Lower Bound (MCRLB), and validate the performance gain of harnessing the NLoS paths.

关键词： Lower bound Message passing Estimation Line-of-sight propagation Mean square error methods Reconfigurable intelligent surfaces Performance gain approximation algorithms Numerical models Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Single Snapshot Direction of Arrival Estimation Using the EP-SURE-SBL Algorithm

Single Snapshot Direction of Arrival Estimation Using the EP...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Fangqing Xiao Dirk Slock Communication Systems Department Eurecom France

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Grid-based methods in sparse signal reconstruction (SSR) are well-regarded for their efficacy in direction-of-arrival (DoA) estimation. This paper presents the EP (Expectation Propagation)-SURE (Stein's Unbiased Risk Estimate)-SBL (Sparse Bayesian Learning) algorithm, designed for single snapshot DoA estimation. The algorithm divides DoA estimation into two parts: grid-on estimation and off-grid error estimation, employing first-order and second-order Taylor expansions. In grid-on estimation, sparse Bayesian learning is employed for sparse modeling. To tackle hyperparameter estimation challenges within sparse Bayesian learning, the algorithm adopts SURE estimator instead of the commonly-used expectation-maximization (EM) approach. For off-grid error estimation, the algorithm utilizes the EP technique to handle high-dimensional, non-tractable integration in posterior mean calculations. The feasibility and effectiveness of the proposed algorithm are validated through extensive simulations.

关键词： Direction-of-arrival estimation Error analysis Estimation Signal processing algorithms Mean square error methods Taylor series approximation algorithms Signal reconstruction Bayes methods Speech processing

来源：评论

学校读者我要写书评

暂无评论

The Problem of Plane Wave Diffraction by an Inhomogeneous Compact Body

The Problem of Plane Wave Diffraction by an Inhomogeneous Co...

引用

Wave Electronics and its Application in Information and Telecommunication Systems (WECONF)

作者： S. A. Manenkov D. V. Krysanov Moscow Technical University of Communications and Informatics Moscow Russia

ISBN: (数字)9781665465687

ISBN: (纸本)9781665465694

Two various versions of the Modified Volume Integral Equation Method (MVIEM) for solving the diffraction problem on a permeable, inhomogeneous body located in free space are presented. The results obtained using these algorithms are compared to those obtained using the Modified Method of Discrete Sources, by the examples of diffraction problems on a homogeneous sphere, homogeneous spheroid, and round cylinder. MVIEM has also applied to non axisymmetrical bodies specifically, the problem of diffraction on an inhomogeneous rectangular parallelepiped.

关键词： Accuracy Diffraction Integral equations Scattering Nonhomogeneous media approximation algorithms Telecommunications

来源：评论

学校读者我要写书评

暂无评论

KartGPS: Knowledge Base Update with Temporal Graph Pattern-based Semantic Rules

KartGPS: Knowledge Base Update with Temporal Graph Pattern-b...

引用

International Conference on Data Engineering

作者： Hao Xin Lei Chen HKUST Hong Kong China HKUST(GZ) & HKUST Hong Kong China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

The rapidly changing nature of information world-wide often leads to incomplete and obsolete knowledge facts stored in knowledge bases (KBs). Therefore, reasoning over the dynamic KB sequences, which targets at knowledge inference from evolving facts, is of great importance to maintain KB completeness as well as freshness. Existing approaches for KB updating mainly either focus on knowledge representation learning methods, which suffer from lack of interpretability, or attempt to mine path-based logical rules, which are limited in capturing structural semantics of KB. In this work, we present KartGPS, a system for KB updating taking advantage of temporal graph pattern-based semantic (tGPS) rules. Specifically, the tGPS rules are learned from KB sequences and thus are capable of capturing both temporal and topological regularities of KBs along the evolving of time. Due to the huge amount and imperfect quality of tGPS rules, directly generating and applying all generated rules in a brute-force manner for knowledge updating over large-scale KB sequences would be highly time-consuming and error-prone. Therefore, we investigate the problem of Knowledge Update Rule Discovery (KURD), which aims at deriving an optimal subset of tGPS rules for performing knowledge updating, considering the rule quality and coverage. We show that the KURD problem is NP-hard and design two effective approximation algorithms with greedy and pruning strategies. We demonstrate the effectiveness and efficiency of proposed approaches by extensive experiments on real-world KB datasets.

关键词： Learning systems Semantics Knowledge based systems Knowledge representation approximation algorithms Data engineering Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

Marginal Fermi liquid behavior at the onset of 2kF density wave order in two-dimensional metals with flat hot spots

arXiv

引用

arXiv 2024年

作者： Debbeler, Lukas Metzner, Walter Max Planck Institute for Solid State Research StuttgartD-70569 Germany

We analyze quantum fluctuation effects at the onset of incommensurate 2kF charge- or spin-density wave order in two-dimensional metals, for a model where the ordering wave vector Q connects a single pair of hot spots on the Fermi surface with a vanishing Fermi surface curvature. The tangential momentum dependence of the bare dispersion near the hot spots is proportional to |kt|α with α > 2. We first compute the order parameter susceptibility and the fermion self-energy in random phase approximation (RPA). Logarithmic divergences are subsequently treated by a renormalization group analysis. The coupling between the order parameter fluctuations and the fermions vanishes logarithmically in the low-energy limit. As a consequence, the logarithmic divergences found in RPA do not sum up to anomalous power laws. Instead, only logarithmic corrections to Fermi liquid behavior are obtained. In particular, the quasiparticle weight and the Fermi velocity vanish logarithmically at the hot spots. © 2024, CC BY.

关键词： approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Decentralized Online Ensembles of Gaussian Processes for Multi-Agent Systems

Decentralized Online Ensembles of Gaussian Processes for Mul...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Fernando Llorente Daniel Waxman Petar M. Djurić Department of Electrical and Computer Engineering Stony Brook University Stony Brook New York USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Flexible and scalable decentralized learning solutions are fundamentally important in the application of multi-agent systems. While several recent approaches introduce (ensembles of) kernel machines in the distributed setting, Bayesian solutions are much more limited. We introduce a fully decentralized, asymptotically exact solution to computing the random feature approximation of Gaussian processes. We further address the choice of hyperparameters by introducing an ensembling scheme for Bayesian multiple kernel learning based on online Bayesian model averaging. The resulting algorithm is tested against Bayesian and frequentist methods on simulated and real-world datasets.

关键词： Signal processing algorithms Gaussian processes Signal processing approximation algorithms Bayes methods Speech processing Kernel machines Kernel Optimization Multi-agent systems

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：