检索结果-内蒙古大学图书馆

16th International Conference Management of Large-Scale System Development, MLSD 2023

作者： Gorelov, Mikhail Federal Research Center 'Computer Science and Control' The Russian Academy of Sciences Department of Information and Computing Systems Moscow Russia

The maximal guaranteed result in a hierarchical game with an undetermined factor is found in the class of strategies with feedback. The stability of the problem under consideration concerning perturbations of the payo... 详细信息

ISBN: (纸本)9798350337907

关键词： hierarchical games with uncertain factors maximal guaranteed result stability

来源：评论

学校读者我要写书评

暂无评论

Enhancing Free-Form Table Question Answering Models by Distilling Relevant-Cell-Based Rationales 23

引用

23rd Chinese National Conference on Computational Linguistics, CCL 2024

作者： Yang, Zhiyu Wang, Shuo Yan, Yukun Liu, Pengyuan Yu, Dong School of Information Science Beijing Language and Culture University China Department of Computer Science and Technology Tsinghua University China National Language Resources Monitoring and Research Center for Print Media China

ISBN: (纸本)9780000000002

Free-form table question answering is a challenging task since tables contain structured contents compared to plain texts, which requires high-level reasoning abilities to effectively identify cells that are relevant to the question and produce a correct and faithful answer based on their relations. Large language models (LLMs) have exhibited remarkable reasoning capabilities in numerous NLP applications. However, in some specific tasks, specially-trained small models can still outperform LLMs. Furthermore, small models require extremely less computation costs compared to LLMs. To leverage the strengths of both types of models, we propose a Relevant-Cell-based Knowledge Distillation with inference-time Teacher Guidance (RCKD-TG) method. This approach aims to combine small free-form table question answering models’ abilities to learn from human annotations and large language models’ abilities to effectively reason from table contents, via applying Relevant-Cell-based rationales distilled from LLMs to small models’ training and inference stages. Our experiments demonstrate the superiority of our method over vanilla small models in correctness, faithfulness, adequacy and fluency, also over general LLMs in adhering to the style of human annotations. We achieve state-of-the-art performance on FeTaQA, a representative free-form table question answering benchmark. Our result of a 41.3 BLEU score demonstrates the feasibility of effectively using small models’ task-specific abilities and LLMs’ reasoning capabilities at the same time. Additionally, our method exhibits high computation efficiency and data efficiency. Compared to strong baselines, we achieve better performance with significantly less training data. © 2024 China National Conference on Computational Linguistics.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Internet Representation of Research Institutions as a Result of science Reform 16

Internet Representation of Research Institutions as a Result...

引用

16th International Conference Management of Large-Scale System Development, MLSD 2023

作者： Medennikov, Viktor Federal Research Center 'Computer Science and Control' of the Russian Academy of Sciences Information and Computing Systems Department Moscow Russia

ISBN: (纸本)9798350337907

The paper considers the condition and comparison of representation on the Internet of both unaffected and reformed research institutions, in order to form a methodology for assessing the possibility of adequate and timely response to the enormous social and economic challenges occurring in the world;for this purpose, websites' content condition and dynamics are analyzed using the example of agricultural research institutions based on monitoring thereof in 2017 and 2022. It is shown that the science reform proved itself inconsistent since at first it did not respond to the demands of production during the pandemic, and now to the requests due to sanctions. The result of the science reform was a significant increase in the number of uninformative websites, which contradicts the new social order that all sectors of society, business, and management generate for digital tools for transferring scientific developments to the economy against the backdrop of severe sanctions and the pandemic. © 2023 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Intelli-farm: IoT based Smart farming using Machine learning approaches 2

Intelli-farm: IoT based Smart farming using Machine learning...

引用

2nd International Conference on Business Analytics for Technology and Security, ICBATS 2023

作者： Tahir, Sidra Hafeez, Yaser Qamar, Farkhanda Alwakid, Ghadah Naif University of Arid Agriculture University Institute of Information Technology Rawalpindi Pakistan Applied Science Private University Applied Science Research Center Amman11937 Jordan Jouf University College of Computer and Information Sciences Department of Computer Science Sakakah42421 Saudi Arabia

ISBN: (纸本)9798350335644

Internet of Things (IoT) technology has transformed every facet of everyday life by making everything smarter. Among the large spectrum of IoT applications, IoT based smart agriculture has interested many researchers and has employed Machine Learning(ML) and IoT technology to undertake unique contributions. IoT based data-driven farm management approaches can assist enhance agricultural yields by managing input costs, decreasing losses, and using resources especially water more efficiently. The IoTs creates a large volume of data with varying properties dependent on location and time. To increase agricultural output through intelligent farm management, data must be thoroughly evaluated and processed. High-performance computing power in ML brings up new options for data-intensive science as the amount of data gathered rises;ML methods might be employed to further enhance application intelligence and usefulness. In this paper, a novel framework named Intelli-farm is proposed which is based on IoT and ML collectively and produces higher accuracy for detecting need of water in a particular farm. Experiments conducted with different training and testing ratio provided an average accuracy of 93.87%. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control 38

Aligning Diffusion Behaviors with Q-functions for Efficient ...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Chen, Huayu Zheng, Kaiwen Su, Hang Zhu, Jun Department of Computer Science and Technology Tsinghua University China Institute for AI BNRist Center Tsinghua-Bosch Joint ML Center THBI Lab Tsinghua University China Guangzhou China

Drawing upon recent advances in language model alignment, we formulate offline Reinforcement Learning as a two-stage optimization problem: First pretraining expressive generative policies on reward-free behavior datasets, then fine-tuning these policies to align with task-specific annotations like Q-values. This strategy allows us to leverage abundant and diverse behavior data to enhance generalization and enable rapid adaptation to downstream tasks using minimal annotations. In particular, we introduce Efficient Diffusion Alignment (EDA) for solving continuous control problems. EDA utilizes diffusion models for behavior modeling. However, unlike previous approaches, we represent diffusion policies as the derivative of a scalar neural network with respect to action inputs. This representation is critical because it enables direct density calculation for diffusion models, making them compatible with existing LLM alignment theories. During policy fine-tuning, we extend preference-based alignment methods like Direct Preference Optimization (DPO) to align diffusion behaviors with continuous Q-functions. Our evaluation on the D4RL benchmark shows that EDA exceeds all baseline methods in overall performance. Notably, EDA maintains about 95% of performance and still outperforms several baselines given only 1% of Q-labelled data during fine-tuning. Code: https://***/thu-ml/Efficient-Diffusion-Alignment. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Food Engineering Through Machine Learning in Analyzing Biomolecular Structures

Enhancing Food Engineering Through Machine Learning in Analy...

引用

2024 International Conference on Decision Aid sciences and Applications, DASA 2024

作者： Shoulek, Reem Ziad Ibrahim, Sajjad Ghalib Khishe, Mohammad Saeed, Ali Ghwanmeh, Sameh Alma'Moon University College Biology Science Department Baghdad Iraq Innovation Center for Artificial Intelligence Applications Yuan Ze University Taiwan Jadara Research Center Jadara University Jordan Computer Center Northern Technical University Ninevah Iraq College of Computer Information Technology American University in the Emirates Computer Science Dept United Arab Emirates

ISBN: (纸本)9798350369106

In this paper, a detailed investigation has been outlined of protein sequence data with the help of a machine learning model for the identification of macromolecule types. The dataset was preprocessed from the Protein Data Bank and included missing values and duplicate structures, and the nominal variables have been encoded. The approach that was used in our study entailed the employment of Random Forest Classifier to forecast macromolecule types using the sequence data. Researchers divided the data into the training and testing data sets, thereafter, training the classifier, they tested the classifier's accuracy, precision, recall, and F1-score metrics. It can be stated that the relevance of this study is based on the necessity to discover the structural and functional properties of proteins in the field of bioinformatics. Hence, through an accurate classification of the macromolecule types, this approach assists in defining and describing the proteins, thus demystifying the roles that they play within biological cells. Our contribution also comprises the derivation of a highly reliable classification model that would be useful in identifying the type of macromolecules present from protein sequences. The model thus made high accurate determination of the different macromolecules and provided a clear framework which showed the model's efficacy in the differentiation of different macromolecules. Also, we describe the results of the analysis of macromolecule types of distribution and reveal the most often used categories within the set. This paper, therefore, demonstrates the potential of ML in bioinformatics and improves knowledge in predicting protein structure and function which may be of value in numerous biomedicine sectors. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Pseudo-Labeling for Unsupervised Meta-Learning

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5475-5488页

作者： Ouyang, Tianran Dong, Xingping Ye, Mang Du, Bo Shao, Ling Shen, Jianbing Wuhan University School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan430072 China University of Chinese Academy of Sciences UCAS-Terminus AI Lab Beijing101408 China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science 314100 China

In unsupervised meta-learning, the clustering-based pseudo-labeling approach is an attractive framework, since it is model-agnostic, allowing it to synergize with supervised algorithms to learn from unlabeled data. However, the pseudo-labels suffer from clustering noise and semantic chaos problems, further impacting the effectiveness of meta-learning. In this paper, we analyze and optimize the pseudo-labeling process, including encoding and clustering, aiming to generate semantic-like pseudo-labels to narrow the gap between unsupervised and supervised meta-learning. First, during the encoding, we observe that the embedding space of existing methods lacks clustering-friendly properties, which is the primary reason for clustering noise. To address this issue, we minimize the inter-to-intra-class similarity ratio to generate clustering-friendly embedding features and validate our approach through comprehensive experiments. Then, during the clustering, we find that the semantic quality of pseudo-labels is not adequately controlled, resulting in semantic chaos of pseudo-labels. We propose a semantic-stability index to measure the semantic quality of pseudo-labels quantitatively. Based on this index, we propose the Semantic-aware Pseudo-label Reassignment mechanism to generate semantic-like pseudo-labels for all samples. Our approach is model-agnostic and can easily be integrated into existing supervised methods. To demonstrate its generalization ability, we integrate it into two representative algorithms: MAML and EP. The results on three main few-shot benchmarks clearly show that the proposed method achieves significant improvement compared to state-of-the-art models. Notably, our approach also outperforms the corresponding supervised method in three tasks. © 1979-2012 IEEE.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Gibbs Sampling gives quantum Advantage at Constant Temperatures with O(1)-Local Hamiltonians

arXiv

引用

arXiv 2024年

作者： Rajakumar, Joel Watson, James D. Joint Center for Quantum Information & Computer Science National Institute of Standards & Technology University of Maryland College Park United States Department of Computer Science Institute for Advanced Computer Studies University of Maryland College Park United States

Sampling from Gibbs states — states corresponding to system in thermal equilibrium — has recently been shown to be a task for which quantum computers are expected to achieve super-polynomial speed-up compared to classical computers, provided the locality of the Hamiltonian increases with the system size [BCL24]. We extend these results to show that this quantum advantage still occurs for Gibbs states of Hamiltonians with O(1)-local interactions at constant temperature by showing classical hardness-of-sampling and demonstrating such Gibbs states can be prepared efficiently using a quantum computer. In particular, we show hardness-of-sampling is maintained even for 5-local Hamiltonians on a 3D lattice. We additionally show that the hardness-of-sampling is robust when we are only able to make imperfect measurements. Copyright © 2024, The Authors. All rights reserved.

关键词： quantum computers

来源：评论

学校读者我要写书评

暂无评论

KSKV:Key-Strategy for Key-Value Data Collection with Local Differential Privacy

引用

computer Modeling in Engineering & sciences 2024年第6期139卷 3063-3083页

作者： Dan Zhao Yang You Chuanwen Luo Ting Chen Yang Liu Artificial Intelligence Development Research Center Institute of Scientific and Technical Information of ChinaBeijing100038China Industry Development Department NSFOCUS Inc.BeijingChina School of Information Science and Technology Beijing Forestry UniversityBeijing100083China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu610054China Institute of Computing Technology China Academy of Railway Sciences Corporation LimitedBeijing10081China

In recent years,the research field of data collection under local differential privacy(LDP)has expanded its focus fromelementary data types to includemore complex structural data,such as set-value and graph ***,our comprehensive review of existing literature reveals that there needs to be more studies that engage with key-value data *** studies would simultaneously collect the frequencies of keys and the mean of values associated with each ***,the allocation of the privacy budget between the frequencies of keys and the means of values for each key does not yield an optimal utility *** the importance of obtaining accurate key frequencies and mean estimations for key-value data collection,this paper presents a novel framework:the Key-Strategy Framework forKey-ValueDataCollection under ***,theKey-StrategyUnary Encoding(KS-UE)strategy is proposed within non-interactive frameworks for the purpose of privacy budget allocation to achieve precise key frequencies;subsequently,the Key-Strategy Generalized Randomized Response(KS-GRR)strategy is introduced for interactive frameworks to enhance the efficiency of collecting frequent keys through group-anditeration *** strategies are adapted for scenarios in which users possess either a single or multiple key-value ***,we demonstrate that the variance of KS-UE is lower than that of existing *** claims are substantiated through extensive experimental evaluation on real-world datasets,confirming the effectiveness and efficiency of the KS-UE and KS-GRR strategies.

关键词： Key-value local differential privacy frequency estimation mean estimation data perturbation

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Particle Swarm Optimization for ITC2021 Sports Timetabling

引用

computers, Materials & Continua 2022年第7期72卷 1995-2014页

作者： Mutasem K.Alsmadi Ghaith M.Jaradat Malek Alzaqebah Ibrahim A.Lmarashdeh Fahad A.Alghamdi Rami Mustafa A.Mohammad Nahier Aldhafferi Abdullah Alqahtani Department of MIS College of Applied Studies and Community ServiceImam Abdulrahman Bin Faisal UniversityDammamSaudi Arabia Department of Computer Science Faculty of Computer Science and InformaticsAmman Arab UniversityAmmanJordan Department of Mathematics College of ScienceImam Abdulrahman Bin Faisal UniversityDammamSaudi Arabia Basic and Applied Scientific Research CenterImam Abdulrahman Bin Faisal UniversityDammamSaudi Arabia Computer Information Systems Department College of Computer Science and Information TechnologyImam Abdulrahman Bin Faisal UniversityDammamSaudi Arabia

Timetabling problem is among the most difficult operational tasks and is an important step in raising industrial productivity,capability,and *** tasks are usually tackled using metaheuristics techniques that provide an intelligent way of suggesting solutions or *** intelligence techniques including Particle Swarm Optimization(PSO)have proved to be effective *** recent experiments showed that the PSO algorithm is reliable for timetabling in many applications such as educational and personnel timetabling,machine scheduling,***,having an optimal solution is extremely challenging but having a sub-optimal solution using heuristics or metaheuristics is *** research paper seeks the enhancement of the PSO algorithm for an efficient timetabling *** algorithm aims at generating a feasible timetable within a reasonable *** enhanced version is a hybrid dynamic adaptive PSO algorithm that is tested on a round-robin tournament known as ITC2021 which is dedicated to sports *** competition includes several soft and hard constraints to be satisfied in order to build a feasible or sub-optimal *** consists of three categories of complexities,namely early,test,and middle *** showed that the proposed dynamic adaptive PSO has obtained feasible timetables for almost all of the *** feasibility is measured by minimizing the violation of hard constraints to *** performance of the dynamic adaptive PSO is evaluated by the consumed computational time to produce a solution of feasible timetable,consistency,and *** dynamic adaptive PSO showed a robust and consistent performance in producing a diversity of timetables in a reasonable computational time.

关键词： Sports timetabling particle swarm optimization ITC2021 roundrobin tournament dynamic adaptive

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：