检索结果-内蒙古大学图书馆

Distribution-flexible subset quantization for post-quantizing super-resolution networks

Science China(Information Sciences) 2025年第3期68卷 163-180页

作者： Yunshan ZHONG Mingbao LIN Jingjing XIE Yuxin ZHANG Fei CHAO Rongrong JI Institute of Artificial Intelligence Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of ChinaXiamen University Tencent Youtu Lab Department of Artificial Intelligence School of Informatics Xiamen University Peng Cheng Laboratory

This paper introduces distribution-flexible subset quantization(DFSQ), a post-training quantization method for super-resolution networks. Our motivation for developing DFSQ is based on the distinctive activation distributions of current super-resolution models, which exhibit significant variance across samples and channels. To address this issue, DFSQ conducts channel-wise normalization of the activations and applies distribution-flexible subset quantization(SQ), wherein the quantization points are selected from a universal set consisting of multi-word additive log-scale values. To expedite the selection of quantization points in SQ, we propose a fast quantization points selection strategy that uses K-means clustering to select the quantization points closest to the centroids. Compared to the common iterative exhaustive search algorithm, our strategy avoids the enumeration of all possible combinations in the universal set, reducing the time complexity from exponential to linear. Consequently, the constraint of time costs on the size of the universal set is greatly relaxed. Extensive evaluations of various super-resolution models show that DFSQ effectively improves performance even without fine-tuning. For example, for 4-bit EDSR×2 on the Urban benchmark, DFSQ obtains 0.242 dB PSNR gains.

关键词： super-resolution post-training quantization distribution-flexible subset quantization neural network

来源：评论

学校读者我要写书评

暂无评论

Applying Theory of Mind to Multi-agent Systems: A Systematic Review 12th

Applying Theory of Mind to Multi-agent Systems: A Systemat...

引用

12th Brazilian Conference on Intelligent Systems, BRACIS 2023

作者： Rocha, Michele da Silva, Heitor Henrique Morales, Analúcia Schiaffino Sarkadi, Stefan Panisson, Alison R. Department of Computing UFSC Florianópolis Brazil Department of Informatics KCL London United Kingdom

ISBN: (纸本)9783031453670

Life in society requires constant communication and coordination. These abilities are efficiently achieved through sophisticated cognitive processes in which individuals are able to reason about the mental attitudes and actions of others. This ability is known as Theory of Mind. Inspired by human intelligence, the field of Artificial Intelligence aims to reproduce these sophisticated cognitive processes in intelligent software agents. In the field of multi-agent systems, intelligent agents are defined not only to execute reasoning cycles inspired by human reasoning but also to work similarly to human society, including aspects of communication, coordination, and organisation. Consequently, it is essential to explore the use of these sophisticated cognitive processes, such as Theory of Mind, in intelligent agents and multi-agent systems. In this paper, we conducted a literature review on how Theory of Mind has been applied to multi-agent systems, and summarise the contributions in this field. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Sustainable energy management in the AI era: a comprehensive analysis of ML and DL approaches

引用

computing 2025年第6期107卷 1-64页

作者： Javed, Haseeb Eid, Fatma El-Sappagh, Shaker Abuhmed, Tamer Department of Computer Science and Engineering College of Computing and Informatics Sungkyunkwan University Suwon Korea Republic of Technology Management Stony Brook University NY11794 United States Applied Artificial Intelligence College of Computing and Informatics Sungkyunkwan University Suwon Korea Republic of Faculty of Computer Science and Engineering Galala University Suez435611 Egypt Information Systems Department Faculty of Computers and Artificial Intelligence Benha University Banha13518 Egypt

This study comprehensively analyzes the application of innovative deep learning (DL) and machine learning (ML) techniques in smart energy management systems (EMSs), with an emphasis on load forecasting, demand response, and the development of smart energy sectors. The application of various ML and DL models were examined in over 200 studies from 2014 to 2024 in an electrical network's EMS to highlight the key benefits and advances made by each technology for the sustainable management systems in energy sector. The findings emphasize DL and ML models’ enhanced precision and predictive capabilities in load forecasting, their efficacy in enabling efficient demand response mechanisms, and their significance in supporting the development of smart energy sectors. Furthermore, recommendations are made based on the survey results to assist in incorporating these techniques into EMS frameworks, such as investment in data infrastructure, model training and validation, and collaboration between researchers, industry experts, and policymakers. The study also discusses the limitations identified in the literature, such as limited real-world implementations, challenges regarding quality and data availability, and the need for enhanced ML and DL model interpretability. Addressing these limitations can assist in increasing the application and efficacy of ML and DL techniques in EMSs, enabling a more efficient and sustainable energy landscape. Finally, this study facilitates researchers' exploration of ML and DL in energy management, highlighting relevant limitations, strengths, and alternative approaches associated with sustainable energy management. It also indicates potential future research directions for further investigation. © The Author(s) 2025.

关键词： Power management (telecommunication)

来源：评论

学校读者我要写书评

暂无评论

Natural Language Processing Revolution From Humble Beginnings to Deep Learning and Beyond 4

Natural Language Processing Revolution From Humble Beginning...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Smarts, Nyalalani Selvaraj, Rajalakshmi Kuthadi, Venumadhav Botswana International University of Science and Technology School of Pure and Applied Sciences Department of Computing and Informatics Palapye Botswana

ISBN: (纸本)9798331518981

This paper explores the intricate development of Natural Language Processing (NLP), a domain which is centered at the core of computational intelligence and human communication. This research is inspired by the need to understand the foundations of NLP and how it has influenced the development of human-computer interactions, language comprehension systems and information retrieval techniques. It explores the transformational effect of deep learning and attention-based models such as the third-generation Generative Pre-trained Transformer (GPT-3), Text-to-Text Transfer Transformer (T5) and Bidirectional Encoder Representations from Transformers (BERT). The models mentioned above have greatly improved the capability to comprehend and generate human-like language using computers. The originality of the work is also reflected on its comprehensive overview of key NLP concepts, tracing chronological advancements, exploring deep learning innovations, and discussing effective pruning techniques to optimize model performance. By reviewing the history of NLP, this research not merely brings the past into focus but suggests future developments for scholars to investigate and find solutions for current challenges in NLP. Its results not only act as a guide for practitioners today but also suggest new directions for research and development that will help meet the challenges of tomorrow in this dynamic discipline of NLP. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

GAProtoNet: A Multi-head Graph Attention-based Prototypical Network for Interpretable Text Classification 31

GAProtoNet: A Multi-head Graph Attention-based Prototypical ...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Wen, Ximing Tan, Wenjuan Weber, Rosina O. College of Computing and Informatics Drexel University Philadelphia United States Department of Computer Science Tsinghua University Beijing China

ISBN: (纸本)9798891761964

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on text classification tasks with their powerful word embeddings, but their black-box nature, which leads to a lack of interpretability, has been a major concern. In this work, we introduce GAProtoNet, a novel white-box Multi-head Graph Attention-based Prototypical Network designed to explain the decisions of text classification models built with LM encoders. In our approach, the input vector and prototypes are regarded as nodes within a graph, and we utilize multi-head graph attention to selectively construct edges between the input node and prototype nodes to learn an interpretable prototypical representation. During inference, the model makes decisions based on a linear combination of activated prototypes weighted by the attention score assigned for each prototype, allowing its choices to be transparently explained by the attention weights and the prototypes. Experiments on multiple public datasets show our approach achieves superior results without sacrificing the accuracy of the original black-box LMs. We also compare with four alternative prototypical network variations and our approach achieves the best accuracy and F1 among all. Our case study and visualization of prototype clusters also demonstrate the efficiency in explaining the decisions of black-box models built with LMs. Our codes are available at https://***/ximingwen/GAProtoNet. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

INTEGRATING UNMANNED AERIAL SYSTEMS INTO THE INTELLIGENT SYSTEMS ENGINEERING CURRICULUM 34th

INTEGRATING UNMANNED AERIAL SYSTEMS INTO THE INTELLIGENT SYS...

引用

34th Congress of the International Council of the Aeronautical Sciences, ICAS 2024

作者： Dantsker, Or D. Department of Intelligent Systems Engineering Luddy School of Informatics Computing and Engineering Indiana University BloomingtonIN United States

This paper presents two hands-on, project-based courses on unmanned aerial systems recently offered by the Intelligent Systems Engineering program at Indiana University. In Fall 2023, ENGR-E399/599 Autonomous Sports was redeveloped to focus on integrated vehicle design and development of lighter-than-air vehicles in a capstone-like, project-based course format. And in Spring 2024, ENGR-E399/599 Unmanned Aerial Systems was developed to introduce students to UAS in a lecture-lab-project format where students learned about underlying aircraft concepts, developed a micro-controller-based autopilot, ultimately integrated it into a small fixed-wing unmanned aircraft that was test flown. These courses, geared towards advanced undergraduate and graduate students, allow them to apply their prerequisite knowledge to these hardware-lab heavy courses, enabling experiential learning, i.e. "learn-by-doing". © 2024, International Council of the Aeronautical Sciences. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Advances and Challenges of Deep Learning

引用

Recent Patents on Engineering 2023年第4期17卷 1-2页

作者： Wang, Shui-Hua Zhang, Yu-Dong School of Computing and Mathematical Sciences Department of Informatics University of Leicester LeicesterLE1 7RH United Kingdom

This editorial presents the recent advances and challenges of deep learning. We reviewed four main challenges: heterogeneity, copious size, reproducibility crisis, and explainability. Finally, we present the prospect ... 详细信息

关键词： Artificial intelligence COVID-19 diagnosis deep learning deep mind ANNs machine learning

来源：评论

学校读者我要写书评

暂无评论

Elucidating Theory of Malaysian Data Crisis in Demystifying Dark Data Catalyst 6

Elucidating Theory of Malaysian Data Crisis in Demystifying ...

引用

6th IEEE Symposium on Computers and informatics, ISCI 2024

作者： Ajis, Ahmad Fuzi Md Ibrahim, Ag. Asri Ag Verma, Manoj Kumar UiTM Cawangan Johor Center of Information Science College of Computing Informatics and Mathematics Segamat Malaysia University Malaysia Sabah Faculty of Computing and Informatics Kota Kinabalu Malaysia Mizoram University Department of Library and Information Science Aizawl India

ISBN: (纸本)9798350353853

This article presents the findings of a research on the dark data phenomenon faced by Small and Medium Enterprises (SME) in Malaysia in connection to the features of dark data from SME perspectives. The dark data was found to be influenced by the data shadow in the form of grey and black data which each differentiated by the intensity of data darkness, a condition that influenced data from being found and utilized. In this study, there were 18 samples produced from Inductive Grounded & Emergent Theory Sampling, which was used to discover acceptable samples for the study, were subjected to qualitative research. Using semi-structured interviews that were recorded, transcribed, and analyzed using the Grounded Theory Methodology, data was obtained. The outcomes of the study emphasized on the emergence of Data Crisis which found to be the major factors contributing to the dark data often found in SME archives. The research demonstrates that there is a dearth of literature on dealing with dark data, indicating that dark data epistemology is still emerging. The findings indicated that the Data Crisis is a situation in which a business proprietor is confronted with the repercussions of inadequate data management. On the basis of the experiences of Malaysian SMEs, a model was proposed to elucidate the data crisis. © 2024 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

SYSTEMATIC REVIEW: OPPORTUNITIES AND CHALLENGES OF MACHINE LEARNING TECHNIQUES FOR CARDIOVASCULAR DISEASE PREDICTION

引用

Xinan Jiaotong Daxue Xuebao/Journal of Southwest Jiaotong University 2024年第2期59卷 97-127页

作者： Qtaishat, Ahmed Wan Awang, Wan Suryani General Foundation Program Department of Information Technology Sohar University Sohar Oman Faculty of Informatics and Computing University Sultan Zainal Abdlidin Besut Campus Besut Terengganu 22200 Malaysia

Access to healthcare is a fundamental pillar of human well-being, yet cardiovascular diseases (CVD) persist as leading contributors to global mortality. This study explores the transformative potential of Machine Learning (ML) and Deep Learning (DL) algorithms in predicting a spectrum of CVDs, encompassing Heart Failure (HF), Arrhythmia, and coronary artery disease (CAD). With a focus on HF identification and associated risk factors, our primary aim is to rigorously evaluate the efficacy of diverse ML and DL models for CVD diagnosis. Through meticulous analysis of varied datasets, we examine different ML and DL methodologies to determine their predictive capabilities in the realm of CVD. Our findings illuminate promising advancements in CVD prediction accuracy, particularly in heart failure identification. Moreover, we elucidated the intricate interplay between cardiac and pulmonary functions in the context of heart disease, shedding light on disease mechanisms and novel diagnostic avenues. The novelty of our research lies in its comprehensive evaluation of ML and DL algorithms across heterogeneous datasets, fostering the refinement of CVD prediction strategies. By elucidating the effectiveness of various approaches, our study offers invaluable insights for healthcare practitioners and researchers striving to optimize CVD diagnosis and management. Ultimately, the integration of advanced computational techniques holds immense promise for bolstering cardiovascular healthcare outcomes and mitigating the global burden of CVD. © 2024 by the authors.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Dataset of Contractual Events in Court Decisions 39

A Dataset of Contractual Events in Court Decisions

引用

39th International Conference on Logic Programming Workshops, ICLP Workshops 2023

作者： Paulino-Passos, Guilherme Satoh, Ken Toni, Francesca Department of Computing Imperial College London United Kingdom Principles of Informatics Research Division National Institute of Informatics Tokyo Japan

The promise of automation of legal reasoning is developing technology that reduces human time required for legal tasks or that improves human performance on such tasks. In order to do so, different methods and systems based on logic programming were developed. However, in order to apply such methods on legal data, it is necessary to provide an interface between human users and the legal reasoning system, and the most natural interface in the legal domain is natural language, in particular, written text. In order to perform reasoning in written text using logic programming methods, it is then necessary to map expressions in text to atoms and predicates in the formal language, a task referred generally as information extraction. In this work, we propose a new dataset for the task of information extraction, in particular event extraction, in court decisions, focusing on contracts. Our dataset captures contractual relations and events that affect them in some way, such as negotiations preceding a (possible) contract, the execution of a contract, or its termination. We conducted text annotation with law students and graduates, resulting in a dataset with 207 documents, 3934 sentences, 4440 entities, and 1794 events. We describe here this resource, the annotation process, its evaluation with inter-annotator agreement metrics, and discuss challenges during the development of this resource and for the future. 2023 Copyright for this paper by its authors.

关键词： Logic programming

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：