检索结果-内蒙古大学图书馆

IEEE Symposium Series on computational Intelligence (SSCI)

作者： Ehsan Rokhsatyazdi Shahryar Rahnamayan Sevil Zanjani Miyandoab Azam Asilian Bidgoli H.R. Tizhoosh Nature-Inspired Computational Intelligence (NICI) Lab Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa ON Canada Department of Engineering Brock University St. Catharines ON Canada Faculty of Science Wilfrid Laurier University Waterloo ON Canada Department of Artificial Intelligence and Informatics Mayo Clinic Rhazes Lab Rochester MN USA

Training Artificial Neural Networks (ANNs) poses a challenging and critical problem in machine learning. Despite the effectiveness of gradient-based learning methods, such as Stochastic Gradient Descent (SGD), in training neural networks, they do have several limitations. For instance, they require differentiable activation functions, and cannot optimize a model based on several independent non-differentiable loss functions simultaneously; for example, the F1-score, which is used during testing, can be used during training when a gradient-free optimization algorithm is utilized. Furthermore, the training (i.e., optimization of weights) in any DNN can be possible with a small size of the training dataset. To address these concerns, we propose an efficient version of the gradient-free Coordinate Search (CS) algorithm, an instance of General Pattern Search (GPS) methods, for training (i.e., optimizing) neural networks. The proposed algorithm can be used with non-differentiable activation functions and tailored to multi-objective/multi-loss problems. Finding the optimal values for weights of ANNs is a large-scale optimization problem. Therefore instead of finding the optimal value for each variable, which is the common technique in classical CS, we accelerate optimization and convergence by bundling the variables (i.e., weights). In fact, this strategy is a form of dimension reduction for optimization problems. Based on the experimental results, the proposed method is comparable with the SGD algorithm, and in some cases, it outperforms the gradient-based approach. Particularly, in situations with insufficient labeled training data, the proposed CS method performs better. The performance plots demonstrate a high convergence rate, highlighting the capability of our suggested method to find a reasonable solution with fewer function calls. As of now, the only practical and efficient way of training ANNs with hundreds of thousands of weights is gradient-based algorithms such

关键词：

来源：评论

学校读者我要写书评

暂无评论

InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation

arXiv

引用

arXiv 2023年

作者： Dong, Jiahua Cong, Yang Sun, Gan Wang, Lixu Lyu, Lingjuan Li, Jun Konukoglu, Ender The State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China The University of Chinese Academy of Sciences Beijing100049 China The Computer Science Department Northwestern University Evanston United States The Sony AI Tokyo108-0075 Japan The School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Computer Vision Lab ETH Zurich Zürich8092 Switzerland

3D object recognition has successfully become an appealing research topic in the real-world. However, most existing recognition models unreasonably assume that the categories of 3D objects cannot change over time in the real-world. This unrealistic assumption may result in significant performance degradation for them to learn new classes of 3D objects consecutively, due to the catastrophic forgetting on old learned classes. Moreover, they cannot explore which 3D geometric characteristics are essential to alleviate the catastrophic forgetting on old classes of 3D objects. To tackle the above challenges, we develop a novel Incremental 3D Object Recognition Network (i.e., InOR-Net), which could recognize new classes of 3D objects continuously via overcoming the catastrophic forgetting on old classes. Specifically, a category-guided geometric reasoning is proposed to reason local geometric structures with distinctive 3D characteristics of each class by leveraging intrinsic category information. We then propose a novel critic-induced geometric attention mechanism to distinguish which 3D geometric characteristics within each class are beneficial to overcome the catastrophic forgetting on old classes of 3D objects, while preventing the negative influence of useless 3D characteristics. In addition, a dual adaptive fairness compensations strategy is designed to overcome the forgetting brought by class imbalance, by compensating biased weights and predictions of the classifier. Comparison experiments verify the state-of-the-art performance of the proposed InOR-Net model on several public point cloud datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Operation Management of More-Electric Aircraft Using Two-stage Stochastic Model Predictive Control

Operation Management of More-Electric Aircraft Using Two-sta...

引用

European Conference on Power Electronics and Applications

作者： Xin Wang Najmeh Bazmohammadi Jason Atkin Serhiy Bozhko Juan C. Vasquez Josep M. Guerrero Department of Electrical and Electronic Engineering Faculty of Engineering University of Nottingham Nottingham UK Center for Research on Microgrids (CROM) AAU Energy Aalborg University Aalborg Denmark Computational Optimisation and Learning Lab School of Computer Science University of Nottingham Nottingham UK

This paper proposes a two-stage stochastic model predictive control (SMPC) for the operation management of more electric aircraft (MEA). The goal is to minimize load shedding and switching activities in the system, considering the uncertainty of load profile, while optimally charging/discharging the battery-based energy storage system (BESS). In addition, several performance evaluation criteria are introduced to evaluate the effectiveness of the proposed approach. According to the results obtained in 50 random scenarios, SMPC leads to less load-shedding time, higher stored energy levels, and lower uncertainty compensation costs compared to its deterministic counterpart.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Empirical Analysis of Bi-directional Wi-Fi Network Performance on Mobile Robots in Indoor Environments

arXiv

引用

arXiv 2021年

作者： Pandey, Pranav Parasuraman, Ramviyas The Heterogeneous Robotics Research Lab Department of Computer Science University of Georgia AthensGA30602 United States

This paper proposes a framework to measure the important metrics (throughput, delay, packet retransmits, signal strength, etc.) to determine Wi-Fi network performance of mobile robots supported by the Robot Operating Systems (ROS) middleware. We analyze the bidirectional network performance of mobile robots through an experimental setup in an indoor environment, where a mobile robot is communicating vital sensor data such as video streaming from the camera(s) and LiDAR scan values to a command station while it navigates an indoor environment through teleoperated velocity commands received from the command station. The experiments evaluate the performance under 2.4 GHz and 5 GHz channels with different placement of Access Points (AP) with up to two network devices on each side. The framework is generalizable to vehicular network evaluation and the discussions and insights from this study apply to the field robotics community, where the wireless network plays a key role in enabling the success of robotic missions in real-world environments. Copyright © 2021, The Authors. All rights reserved.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Overview of Speaker Modeling and Its Applications: From the Lens of Deep Speaker Representation Learning

arXiv

引用

arXiv 2024年

作者： Wang, Shuai Chen, Zhengyang Lee, Kong Aik Qian, Yanmin Li, Haizhou Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Guangdong Shenzhen518172 China Auditory Cognition and Computational Acoustics Lab The Department of Computer Science and Engineering The MoE Key Laboratory of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Hong Kong

Speaker individuality information is among the most critical elements within speech signals. By thoroughly and accurately modeling this information, it can be utilized in various intelligent speech applications, such as speaker recognition, speaker diarization, speech synthesis, and target speaker extraction. In this overview, we present a comprehensive review of neural approaches to speaker representation learning from both theoretical and practical perspectives. Theoretically, we discuss speaker encoders ranging from supervised to self-supervised learning algorithms, standalone models to large pretrained models, pure speaker embedding learning to joint optimization with downstream tasks, and efforts toward interpretability. Practically, we systematically examine approaches for robustness and effectiveness, introduce and compare various open-source toolkits in the field. Through the systematic and comprehensive review of the relevant literature, research activities, and resources, we provide a clear reference for researchers in the speaker characterization and modeling field, as well as for those who wish to apply speaker modeling techniques to specific downstream tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Robust Model Predictive Control with Control Barrier Functions for Autonomous Surface Vessels

Robust Model Predictive Control with Control Barrier Functio...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Wei Wang Wei Xiao Alejandro Gonzalez-Garcia Jan Swevers Carlo Ratti Daniela Rus Computer Science and Artificial Intelligence Lab (CSAIL) Massachusetts Institute of Technology Cambridge MA USA SENSEable City Laboratory Massachusetts Institute of Technology Cambridge MA USA Marine Robotics Lab Department of Mechanical Engineering College of Engineering University of Wisconsin-Madison Madison WI USA Department of Mechanical Engineering MECO Research Team KU Leuven Belgium Flanders Make@KU Leuven Belgium

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

In autonomous robot navigation, the trajectories from path planners are considered to be safe regions, and deviations could endanger vessels. Model Predictive Control (MPC) stands as a popular choice for trajectory tracking problems as it naturally addresses operational constraints, such as dynamics and control constraints. Nevertheless, achieving robustness in changing environments like oceans and rivers, which are constantly subject to significant external disturbances, remains an ongoing challenge for MPC. It must consistently keep the system within a predefined safe region (such as a reference trajectory) even in the presence of model inaccuracies and perturbations. To address this challenge, we present a robust model predictive control strategy utilizing Control Barrier Functions (CBFs), which increases the disturbance-rejection abilities. We verify our method on an autonomous surface vessel in simulation and natural waters, both with external disturbances. Specifically, compared with the traditional MPC method, our proposed MPC-CBF strategy reduces tracking errors by 17.82% and 40.26% in simulations and field experiments, respectively. Although the control effort slightly increases by 7.78% and 4.20%, respectively, these results clearly demonstrate the enhanced resilience of MPC-CBF to disturbances.

关键词： Sea surface Trajectory tracking Navigation Perturbation methods Robustness Trajectory Rivers

来源：评论

学校读者我要写书评

暂无评论

RCSB Protein Data Bank: revolutionising drug discovery and design for over five decades

引用

Medical Data Mining 2025年第2期8卷 9-20页

作者： Shaban Ahmad Nagmi Bano Khalid Raza Computational Intelligence and Bioinformatics Lab Department of Computer ScienceJamia Millia IslamiaNew Delhi 110025India

In the year 1971,the world’s biggest structural biology collaboration name—The Research Collaboratory for Structural Bioinformatics(RCSB),was formed to gather all the structural biologists at a single platform and then extended out to be the world’s most extensive structural data repository named RCSB-Protein Data Bank(PDB)(https://***/)that has provided the service for more than 50 years and continues its legacy for the discoveries and repositories for structural *** RCSB has evolved from being a collaboratory network to a full-fledged database and tool with a huge list of protein structures,nucleic acid-containing structures,ModelArchive,and AlphaFold structures,and the best is that it is expanding day by day with computational advancement with tools and visual *** this review article,we have discussed how RCSB has been a successful collaboratory network,its expansion in each decade,and how it has helped the ground-breaking *** PDB tools that are helping the researchers,yearly data deposition,validation,processing,and suggestions that can help the developer improve for upcoming years are also *** review will help future researchers understand the complete history of RCSB and its developments in each decade and how various future collaborative networks can be developed in various scientific areas and can be successful by keeping RCSB as a case study.

关键词： Research Collaboratory for Structural Bioinformatics Protein Data Bank crystallography structural biology database drug design

来源：评论

学校读者我要写书评

暂无评论

Analysis of exploration vs. Exploitation in adaptive information sampling

arXiv

引用

arXiv 2021年

作者： Munir, Aiman Parasuraman, Ramviyas the Heterogeneous Robotics Research Lab Department of Computer Science University of Georgia AthensGA30602 United States

Adaptive information sampling approaches enable efficient selection of mobile robot’s waypoints through which accurate sensing and mapping of a physical process, such as the radiation or field intensity, can be obtained. This paper analyzes the role of exploration and exploitation in such information-theoretic spatial sampling of the environmental processes. We use Gaussian processes to predict and estimate predictions with confidence bounds, thereby determining each point’s informativeness in terms of exploration and exploitation. Specifically, we use a Gaussian process regression model to sample the Wi-Fi signal strength of the environment. For different variants of the informative function, we extensively analyze and evaluate the effectiveness and efficiency of information mapping through two different initial trajectories in both single robot and multi-robot settings. The results provide meaningful insights in choosing appropriate information function based on sampling objectives. Copyright © 2021, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning

arXiv

引用

arXiv 2024年

作者： Zimmerman, Julia Witte Hudon, Denis Cramer, Kathryn Ruiz, Alejandro J. Beauregard, Calla Fehr, Ashley Fudolig, Mikaela Irene Demarest, Bradford Bird, Yoshi Meke Trujillo, Milo Z. Danforth, Christopher M. Dodds, Peter Sheridan Computational Story Lab Vermont Complex Systems Institute University of Vermont BurlingtonVT05405 United States Vermont Complex Systems Institute University of Vermont BurlingtonVT05405 United States The Luddite *** Department of Computer Science St. Michael’s College ColchesterVT05439 United States Communication Media and Marginalization Lab Northeastern University BostonMA02215 United States Department of Mathematics & Statistics University of Vermont BurlingtonVT05405 United States Department of Computer Science University of Vermont BurlingtonVT05405 United States

Tokenization is a necessary component within the current architecture of many language models, including the transformer-based large language models (LLMs) of Generative AI, yet its impact on the model’s cognition is often overlooked. We argue that LLMs demonstrate that the Distributional Hypothesis (DH) is sufficient for reasonably human-like language performance, and that the emergence of human-meaningful linguistic units among tokens and current structural constraints motivate changes to existing, linguistically-agnostic tokenization techniques, particularly with respect to their roles as (1) semantic primitives and as (2) vehicles for conveying salient distributional patterns from human language to the model. We explore tokenizations from a BPE tokenizer;extant model vocabularies obtained from Hugging Face and tiktoken;and the information in exemplar token vectors as they move through the layers of a RoBERTa (large) model. Besides creating suboptimal semantic building blocks and obscuring the model’s access to the necessary distributional patterns, we describe how tokens and pretraining can act as a backdoor for bias and other unwanted content, which current alignment practices may not remediate. Additionally, we relay evidence that the tokenization algorithm’s objective function impacts the LLM’s cognition, despite being arguably meaningfully insulated from the main system intelligence. [First uploaded to arXiv in December, 2024.] Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

GRAINS: Proximity Sensing of Objects in Granular Materials

arXiv

引用

arXiv 2023年

作者： Zhang, Zeqing Jia, Ruixing Yan, Youcan Han, Ruihua Lin, Shijie Jiang, Qian Zhang, Liangjun Pan, Jia Department of Computer Science The University of Hong Kong Hong Kong Interactive Digital Humans group LIRMM CNRS-University of Montpellier Montpellier France Department of Mechanical Engineering The Hong Kong Polytechnic University Hong Kong Robotics and Autonomous Driving Lab of Baidu Research Sunnyvale United States

Proximity sensing detects an object's presence without contact. However, research has rarely explored proximity sensing in granular materials (GM) due to GM's lack of visual and complex properties. In this paper, we propose a granular-material-embedded autonomous proximity sensing system (GRAINS) based on three granular phenomena (fluidization, jamming, and failure wedge zone). GRAINS can automatically sense buried objects beneath GM in real-time manner (at least ~20 hertz) and perceive them 0.5 ~ 7 centimeters ahead in different granules without the use of vision or touch. We introduce a new spiral trajectory for the probe raking in GM, combining linear and circular motions, inspired by a common granular fluidization technique. Based on the observation of force-raising when granular jamming occurs in the failure wedge zone in front of the probe during its raking, we employ Gaussian process regression to constantly learn and predict the force patterns and detect the force anomaly resulting from granular jamming to identify the proximity sensing of buried objects. Finally, we apply GRAINS to a Bayesian-optimization-algorithm-guided exploration strategy to successfully localize underground objects and outline their distribution using proximity sensing without contact or digging. This work offers a simple yet reliable method with potential for safe operation in building habitation infrastructure on an alien planet without human intervention. © 2023, CC BY-NC-ND.

关键词： Granular materials

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：