检索结果-内蒙古大学图书馆

12th International Conference on Learning Representations, ICLR 2024

作者： Yu, Annan Nigmetov, Arnur Morozov, Dmitriy Mahoney, Michael W. Erichson, N. Benjamin Center for Applied Mathematics Cornell University IthacaNY14853 United States Lawrence Berkeley National Laboratory BerkeleyCA94720 United States International Computer Science Institute BerkeleyCA94704 United States Department of Statistics University of California at Berkeley BerkeleyCA94720 United States

State-space models (SSMs) have recently emerged as a framework for learning long-range sequence tasks. An example is the structured state-space sequence (S4) layer, which uses the diagonal-plus-low-rank structure of the HiPPO initialization framework. However, the complicated structure of the S4 layer poses challenges;and, in an effort to address these challenges, models such as S4D and S5 have considered a purely diagonal structure. This choice simplifies the implementation, improves computational efficiency, and allows channel communication. However, diagonalizing the HiPPO framework is itself an ill-posed problem. In this paper, we propose a general solution for this and related ill-posed diagonalization problems in machine learning. We introduce a generic, backward-stable "perturb-then-diagonalize" (PTD) methodology, which is based on the pseudospectral theory of non-normal operators, and which may be interpreted as the approximate diagonalization of the non-normal matrices defining SSMs. Based on this, we introduce the S4-PTD and S5-PTD models. Through theoretical analysis of the transfer functions of different initialization schemes, we demonstrate that the S4-PTD/S5-PTD initialization strongly converges to the HiPPO framework, while the S4D/S5 initialization only achieves weak convergences. As a result, our new models show resilience to Fourier-mode noise-perturbed inputs, a crucial property not achieved by the S4D/S5 models. In addition to improved robustness, our S5-PTD model averages 87.6% accuracy on the Long-Range Arena benchmark, demonstrating that the PTD methodology helps to improve the accuracy of deep learning models. © 2024 12th International Conference on Learning Representations, ICLR 2024. 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

Dynamic UAV Phenotyping for Rice Disease Resistance Analysis Based on Multisource Data

引用

Plant Phenomics 2023年第1期5卷 110-122页

作者： Xiulin Bai Hui Fang Yong He Jinnuo Zhang Mingzhu Tao Qingguan Wu Guofeng Yang Yuzhen Wei Yu Tang Lie Tang Binggan Lou Shuiguang Deng Yong Yang Xuping Feng College of Biosystems Engineering and Food Science Zhejiang UniversityHangzhou 310058China Huzhou Institute of Zhejiang University Huzhou 313000China School of Information Engineering Huzhou UniversityHuzhou 313000China Academy of Interdisciplinary Studies Guangdong Polytechnic Normal UniversityGuangzhou 510665China Department of Agricultural and Biosystems Engineering Iowa State UniversityAmesIA 50011-3270USA College of Agriculture and Biotechnology Zhejiang UniversityHangzhou 310058China College of Computer Science and Technology Zhejiang UniversityHangzhou 310058China State Key Laboratory for Managing Biotic and Chemical Treats to the Quality and Safety of Agro-Products Key Laboratory of Biotechnology for Plant ProtectionMinistry of Agricultureand Rural AffairsZhejiang Provincial Key Laboratory of Biotechnology for Plant ProtectionInstitute of Virology and BiotechnologyZhejiang Academy of Agricultural ScienceHangzhou 31002China

Bacterial blight poses a threat to rice production and food security,which can be controlled through large-scale breeding efforts toward resistant *** aerial vehicle(UAV)remote sensing provides an alternative means for the infield phenotype evaluation of crop disease resistance to relatively time-consuming and laborious traditional ***,the quality of data acquired by UAV can be affected by several factors such as weather,crop growth period,and geographical location,which can limit their utility for the detection of crop disease and resistant ***,a more effective use of UAV data for crop disease phenotype analysis is *** this paper,we used time series UAV remote sensing data together with accumulated temperature data to train the rice bacterial blight severity evaluation *** best results obtained with the predictive model showed an R_(p)^(2) of 0.86 with an RMSE_(p) of ***,model updating strategy was used to explore the scalability of the established model in different geographical *** percent of transferred data for model training was useful for the evaluation of disease severity over different *** addition,the method for phenotypic analysis of rice disease we built here was combined with quantitative trait loci(QTL)analysis to identify resistance QTL in genetic populations at different growth *** new QTLs were identified,and QTLs identified at different growth stages were *** analysis combined with UAV high-throughput phenotyping provides new ideas for accelerating disease resistance breeding.

关键词： blight breeding cultivar

来源：评论

学校读者我要写书评

暂无评论

The Evolution of Administrative Information Systems: Assessing the Revolutionary Impact of Artificial Intelligence 7

The Evolution of Administrative Information Systems: Assessi...

引用

7th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2023

作者： Mahmood, Noor.Z. Ahmed, Saadaldeen Rashid Al-Hayaly, Ali Faiek Algburi, Sameer Rasheed, Jawad College of Business and Economics Bayan University Department of Business Administration Kurdistan Region Erbil Iraq College of Engineering and Science Bayan University Department of Computer Science Kurdistan Region Erbil Iraq Al-Kitab University College of Engineering Techniques Iraq Bogazici University Deep Learning and Medical Image Analysis Laboratory Istanbul34342 Turkey

ISBN: (纸本)9798350342154

In the rapidly evolving landscape of organizational technologies, the integration of Artificial Intelligence (AI) into Administrative Information Systems (AIS) stands out as a pivotal and transformative development. This research explores the historical trajectory of AI and its dynamic interplay with AIS, employing a combination of historical analysis, case studies, and in-depth examinations. Our findings reveal the substantial impact of AI on administrative efficiency and decision-making processes, showcasing successful implementations in diverse organizational settings. Concurrently, the study addresses the challenges and ethical considerations accompanying this integration, contributing to a nuanced understanding of the promises and pitfalls of AI in administrative contexts. Beyond retrospective analysis, the research speculates on future trends and innovations, providing insights that inform practitioners, policymakers, and scholars about the multifaceted implications of AI for modern organizations. © 2023 IEEE.

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

LKM-UNet: Large Kernel Vision Mamba UNet for Medical Image Segmentation

arXiv

引用

arXiv 2024年

作者： Wang, Jinhong Chen, Jintai Chen, Danny Wu, Jian College of Computer Science and Technology Zhejiang University China Institute of Wenzhou Zhejiang University China Computer Science Department University of Illinois Urbana-Champaign United States Department of Computer Science and Engineering University of Notre Dame United States State Key Laboratory of Transvascular Implantation Devices of The Second Affiliated Hospital Zhejiang University School of Medicine China School of Public Health Zhejiang University China

In clinical practice, medical image segmentation provides useful information on the contours and dimensions of target organs or tissues, facilitating improved diagnosis, analysis, and treatment. In the past few years, convolutional neural networks (CNNs) and Transformers have dominated this area, but they still suffer from either limited receptive fields or costly long-range modeling. Mamba, a State Space Sequence Model (SSM), recently emerged as a promising paradigm for long-range dependency modeling with linear complexity. In this paper, we introduce a Large Kernel vision Mamba U-shape Network, or LKM-UNet, for medical image segmentation. A distinguishing feature of our LKM-UNet is its utilization of large Mamba kernels, excelling in locally spatial modeling compared to small kernel-based CNNs and Transformers, while maintaining superior efficiency in global modeling compared to self-attention with quadratic complexity. Additionally, we design a novel hierarchical and bidirectional Mamba block to further enhance Mamba’s global and neighborhood spatial modeling capability for vision inputs. Comprehensive experiments demonstrate the feasibility and the effectiveness of using large-size Mamba kernels to achieve large receptive fields. Codes are available at https://***/wjh892521292/LKM-UNet. © 2024, CC BY-NC-SA.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading

arXiv

引用

arXiv 2024年

作者： Zhang, Wenhao Wang, Jun Luo, Yong Yu, Lei Yu, Wei He, Zheng Shen, Jialie School of Computer Science National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China School of Electronics and Information Wuhan University China Department of Computer Science City University of London United Kingdom

Lip-reading is to utilize the visual information of the speaker’s lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different frame rate branches to learn spatio-temporal features of varying granularities. However, aggregating events into event frames inevitably leads to the loss of fine-grained temporal information within frames. To remedy this drawback, we propose a novel framework termed Multi-view Temporal Granularity aligned Aggregation (MTGA). Specifically, we first present a novel event representation method, namely time-segmented voxel graph list, where the most significant local voxels are temporally connected into a graph list. Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated. Finally, we design a temporal aggregation module that incorporates positional encoding, which enables the capture of local absolute spatial and global temporal information. Experiments demonstrate that our method outperforms both the event-based and video-based lip-reading counterparts. Copyright © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Optimal Actuator Attacks on Autonomous Vehicles Using Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Wang, Pengyu Li, Jialu Shi, Ling Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Shenzhen Key Laboratory of Robotics Perception and Intelligence The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

With the increasing prevalence of autonomous vehicles (AVs), their vulnerability to various types of attacks has grown, presenting significant security challenges. In this paper, we propose a reinforcement learning (RL)-based approach for designing optimal stealthy integrity attacks on AV actuators. We also analyze the limitations of state-of-the-art RL-based secure controllers developed to counter such attacks. Through extensive simulation experiments, we demonstrate the effectiveness and efficiency of our proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Tac-VGNN: A Voronoi Graph Neural Network for Pose-Based Tactile Servoing

arXiv

引用

arXiv 2023年

作者： Fan, Wen Yang, Max Xing, Yifan Lepora, Nathan F. Zhang, Dandan The Department of Engineering Mathematics and Bristol Robotics Laboratory University of Bristol United Kingdom The Department of Computer Science University of Bristol United Kingdom

Tactile pose estimation and tactile servoing are fundamental capabilities of robot touch. Reliable and precise pose estimation can be provided by applying deep learning models to high-resolution optical tactile sensors. Given the recent successes of Graph Neural Network (GNN) and the effectiveness of Voronoi features, we developed a Tactile Voronoi Graph Neural Network (Tac-VGNN) to achieve reliable pose-based tactile servoing relying on a biomimetic optical tactile sensor (TacTip). The GNN is well suited to modeling the distribution relationship between shear motions of the tactile markers, while the Voronoi diagram supplements this with area-based tactile features related to contact depth. The experiment results showed that the Tac-VGNN model can help enhance data interpretability during graph generation and model training efficiency significantly than CNN-based methods. It also improved pose estimation accuracy along vertical depth by 28.57% over vanilla GNN without Voronoi features and achieved better performance on the real surface following tasks with smoother robot control trajectories. For more project details, please view our website: https://***/view/tac-vgnn/home Copyright © 2023, 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

Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data

arXiv

引用

arXiv 2024年

作者： Min, Dehai Hu, Nan Jin, Rihui Lin, Nuo Chen, Jiaoyan Chen, Yongrui Li, Yu Qi, Guilin Li, Yun Li, Nijun Wang, Qianren School of Computer Science and Engineering Southeast University China Department of Computer Science The University of Manchester United Kingdom Advanced Cognitive AI Lab Huawei Technologies China Key Laboratory of New Generation Artificial Intelligence Technology Southeast University Ministry of Education China

Augmenting Large Language Models (LLMs) for Question Answering (QA) with domain specific data has attracted wide attention. However, domain data often exists in a hybrid format, including text and semi-structured tables, posing challenges for the seamless integration of information. Table-to-Text Generation is a promising solution by facilitating the transformation of hybrid data into a uniformly text-formatted corpus. Although this technique has been widely studied by the NLP community, there is currently no comparative analysis on how corpora generated by different table-to-text methods affect the performance of QA systems. In this paper, we address this research gap in two steps. First, we innovatively integrate table-to-text generation into the framework of enhancing LLM-based QA systems with domain hybrid data. Then, we utilize this framework in real-world industrial data to conduct extensive experiments on two types of QA systems (DSFT and RAG frameworks) with four representative methods: Markdown format, Template serialization, TPLM-based method, and LLM-based method. Based on the experimental results, we draw some empirical findings and explore the underlying reasons behind the success of some methods. We hope the findings of this work will provide a valuable reference for the academic and industrial communities in developing robust QA systems. Copyright © 2024, The Authors. All rights reserved.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Specific Emitter Identification Based on Joint Variational Mode Decomposition

Specific Emitter Identification Based on Joint Variational M...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Xiaofang Chen Wenbo Xu Yue Wang Key Laboratory of Universal Wireless Communication Beijing University of Posts and Telecommunications Beijing China Department of Computer Science Georgia State University Atlanta GA

ISBN: (数字)9798331517786

ISBN: (纸本)9798331517793

Specific emitter identification (SEI) technology is significant in device administration scenarios, such as self-organized networking and spectrum management, owing to its high security. For nonlinear and non-stationary electromagnetic signals, SEI often employs variational modal decomposition (VMD) to decompose the signal in order to effectively characterize the distinct device fingerprint. However, it has not been well investigated in noisy SEI scenarios. Specifically, the existing VMD algorithms do not utilize the stability of the intrinsic distortion of emitters within a certain temporal span, nor do they consider the vulnerability of this distortion estimates to channel noise, both of which constrain its practical applicability in SEI. In this paper, we propose a joint variational modal decomposition (JVMD) algorithm, which is an improved version of VMD by simultaneously implementing modal decomposition and channel noise estimation on multi-frame signals. The consistency of multi-frame signals in terms of the central frequencies and the inherent modal functions (IMFs) is exploited, which effectively highlights the distinctive characteristics among emitters. In addition, channel noise is estimated during signal decomposition, which improves the ability to stably extract these distinctive characteristics. Additionally, the complexity of JVMD is analyzed, which is proven to be more computational-friendly than VMD. Simulations of both modal decomposition and SEI that involve real-world datasets are presented to illustrate that when compared with other SEI schemes, the JVMD-based scheme improves the accuracy of device classification at low SNRs.

关键词： Vehicular and wireless technologies Time-frequency analysis Accuracy Noise Nonlinear distortion Channel estimation Fingerprint recognition Feature extraction Stability analysis Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Compositional Exemplars for In-context Learning

arXiv

引用

arXiv 2023年

作者： Ye, Jiacheng Wu, Zhiyong Feng, Jiangtao Yu, Tao Kong, Lingpeng Department of Computer Science The University of Hong Kong Hong Kong Shark-NLP Shanghai Artificial Intelligence Laboratory China

Large pretrained language models (LMs) have shown impressive In-Context Learning (ICL) ability, where the model learns to do an unseen task via a prompt consisting of input-output examples as the demonstration, without any parameter updates. The performance of ICL is highly dominated by the quality of the selected in-context examples. However, previous selection methods are mostly based on simple heuristics, leading to sub-optimal performance. In this work, we formulate in-context example selection as a subset selection problem. We propose CEIL (Compositional Exemplars for In-context Learning), which is instantiated by Determinantal Point Processes (DPPs) to model the interaction between the given input and in-context examples, and optimized through a carefully-designed contrastive learning objective to obtain preference from LMs. We validate CEIL on 12 classification and generation datasets from 7 distinct NLP tasks, including sentiment analysis, paraphrase detection, natural language inference, commonsense reasoning, open-domain question answering, code generation, and semantic parsing. Extensive experiments demonstrate not only the state-of-the-art performance but also the transferability and compositionality of CEIL, shedding new light on in-context learning. Our code is released at https://***/HKUNLP/icl-ceil. Copyright © 2023, The Authors. All rights reserved.

关键词： Sentiment analysis

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：