检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Fornasier, Massimo Sun, Lukang Technical University of Munich School of Computation Information and Technology Department of Mathematics Munich Germany Munich Center for Machine Learning Munich Germany Munich Data Science Institute Germany

Introduced in 2017 [28], Consensus-Based Optimization (CBO) has rapidly emerged as a significant breakthrough in global optimization. This straightforward yet powerful multi-particle, zero-order optimization method draws inspiration from Simulated Annealing and Particle Swarm Optimization. Using a quantitative mean-field approximation, CBO dynamics can be described by a nonlinear Fokker-Planck equation with degenerate diffusion, which does not follow a gradient flow structure. In this paper, we demonstrate that solutions to the CBO equation remain positive and maintain full support. Building on this foundation, we establish the unconditional global convergence of CBO methods to global minimizers. Our results are derived through an analysis of solution regularity and the proof of existence for smooth, classical solutions to a broader class of drift-diffusion equations, despite the challenges posed by degenerate diffusion. © 2025, CC BY.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Summarization of Investment Reports Using Pre-trained Model 14

Summarization of Investment Reports Using Pre-trained Model

引用

14th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2023

作者： Sakaji, Hiroki Kobayashi, Ryotaro Izumi, Kiyoshi Mitsugi, Hiroyuki Kuramoto, Wataru The University of Tokyo School of Engineering Tokyo Japan Daiwa Institute of Research Ltd. Frontier Technologies Research Center. Data-driven Science Dept. Tokyo Japan Daiwa Asset Management Co.Ltd. Fund Management Division Tokyo Japan

ISBN: (纸本)9798350324228

In this paper, we attempt to summarize monthly reports as investment reports. Fund managers have a wide range of tasks, one of which is the preparation of investment reports. In addition to preparing monthly reports on fund management, fund managers prepare management reports that summarize these monthly reports every six months or once a year. The preparation of fund reports is a labor-intensive and time-consuming task. Therefore, in this paper, we tackle investment summarization from monthly reports using transformer-based models. There are two main types of summarization methods: extractive summarization and abstractive summarization, and this study constructs both methods and examines which is more useful in summarizing investment reports. © 2023 IEEE.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Examining University Faculty's Acceptance of ChatGPT Through the Technology Acceptance Model

Examining University Faculty's Acceptance of ChatGPT Through...

引用

Information Engineering (ACIE), IEEE Asia Conference on

作者： Zhenhai He Shaoming Chai School of Information Technology in Education South China Normal University Guangzhou China Aberdeen Institute of Data Science and Artificial Intelligence South China Normal University Guangzhou China

ISBN: (数字)9798331528409

ISBN: (纸本)9798331528416

With the increasing integration of ChatGPT into higher education, understanding faculty members' acceptance intentions toward this technology has become a critical area of inquiry. Grounded in the Technology Acceptance Model (TAM), this study analyzed survey data from 264 Chinese university faculty members using structural equation modeling to explore their acceptance intentions regarding ChatGPT for teaching and research. The findings revealed three key insights: (1) Faculty members demonstrated a “high willingness to use - cautious attitude” pattern, indicating a rational balance between the perceived value of the technology and its ethical risks. (2) Training support was identified as a crucial mediating factor influencing faculty members' acceptance intentions. (3) To foster the responsible use of ChatGPT in higher education, the study recommends the development of pedagogy-oriented AI support systems tailored to faculty needs. By expanding the application of TAM theory to educational contexts, this study provides valuable theoretical and practical guidance for the responsible and effective adoption of ChatGPT in higher education.

关键词： Training Surveys Ethics Technology acceptance model Generative AI Education Asia Chatbots Mathematical models data models

来源：评论

学校读者我要写书评

暂无评论

VC Theory for Inventory Policies

arXiv

引用

arXiv 2024年

作者： Xie, Yaqi Ma, Will Xin, Linwei Booth School of Business University of Chicago ChicagoIL60637 United States Graduate School of Business Data Science Institute Columbia University New York10027 United States

Advances in computational power and AI have increased interest in reinforcement learning approaches to inventory management. This paper provides a theoretical foundation for these approaches and investigates the benefits of restricting to policy structures that are well-established by decades of inventory theory. In particular, we prove generalization guarantees for learning several well-known classes of inventory policies, including base-stock and (s,S) policies, by leveraging the celebrated Vapnik-Chervonenkis (VC) theory. We apply the concepts of the Pseudo-dimension and Fat-shattering dimension from VC theory to determine the generalization error of inventory policies, that is, the difference between an inventory policy's performance on training data and its expected performance on unseen data. We focus on a classical setting without contexts, but allow for an arbitrary distribution over demand sequences and do not make any assumptions such as independence over time. We corroborate our supervised learning results using numerical simulations. Managerially, our theory and simulations translate to the following insights. First, there is a principle of "learning less is more" in inventory management: depending on the amount of data available, it may be beneficial to restrict oneself to a simpler, albeit suboptimal, class of inventory policies to minimize overfitting errors. Second, the number of parameters in a policy class may not be the correct measure of overfitting error: in fact, the class of policies defined by T time-varying base-stock levels exhibits a generalization error an order of magnitude lower than that of the two-parameter (s,S) policy class. Finally, our research suggests situations in which it could be beneficial to incorporate the concepts of base-stock and inventory position into black-box learning machines, instead of having these machines directly learn the order quantity actions. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DiffMEL: A large-scale difficulty-graded dataset for Multimodal Entity Linking

DiffMEL: A large-scale difficulty-graded dataset for Multimo...

引用

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

作者： Fang Wang Xiaoying Bai Tianwei Yan Minghao Hu Yi Liang School of Computer Science Peking University Beijing China Advanced Institute of Big Data Beijing (AIBD) Beijing China College of Computer National University of Defense Technology Changsha China School of Computer Science and Technology Xinjiang University Urumqi China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Multimodal Large Language Models (MLLMs) have shown tremendous potential in Multimodal Entity Linking (MEL). However, they are still far from achieving the expected effectiveness in practical applications. This could be due to limitations in the MEL dataset used for training. Existing MEL datasets primarily focus on simple tasks and only consider the direct matching of mentions with labeled entities within a multimodal context, ignoring mentions of unmatched entities. Factors such as the presence of the ground-truth entity within the candidate set and its position directly impact the performance of MLLMs on MEL tasks. To tackle these obstacles, we constructed DiffMEL, the first large-scale difficulty-graded dataset for MEL of MLLMs. DiffMEL contains 79,625 instances and 318.5K instance-related high-resolution images, covering 3 various difficulty graded linking tasks and 5 different entity themes. We utilize DiffMEL to train several open-source MLLMs. Experiment results demonstrate DiffMEL empowers MLLMs with stronger capabilities in MEL by a large-margin (5%-56.1%). our dataset is now available at https://***/ww-ffff/DiffMEL.

关键词： Training Visualization Scalability Large language models Signal processing Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Versatile Weight Attack via Flipping Limited Bits

arXiv

引用

arXiv 2022年

作者： Bai, Jiawang Wu, Baoyuan Li, Zhifeng Xia, Shu-Tao The Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen518057 China The School of Data Science Chinese University of Hong Kong Shenzhen China The Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data 518100 China Tencent Data Platform Shenzhen518057 China

To explore the vulnerability of deep neural networks (DNNs), many attack paradigms have been well studied, such as the poisoning-based backdoor attack in the training stage and the adversarial attack in the inference stage. In this paper, we study a novel attack paradigm, which modifies model parameters in the deployment stage. Considering the effectiveness and stealthiness goals, we provide a general formulation to perform the bit-flip based weight attack, where the effectiveness term could be customized depending on the attacker's purpose. Furthermore, we present two cases of the general formulation with different malicious purposes, i.e., single sample attack (SSA) and triggered samples attack (TSA). To this end, we formulate this problem as a mixed integer programming (MIP) to jointly determine the state of the binary bits (0 or 1) in the memory and learn the sample modification. Utilizing the latest technique in integer programming, we equivalently reformulate this MIP problem as a continuous optimization problem, which can be effectively and efficiently solved using the alternating direction method of multipliers (ADMM) method. Consequently, the flipped critical bits can be easily determined through optimization, rather than using a heuristic strategy. Extensive experiments demonstrate the superiority of SSA and TSA in attacking DNNs. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

PFortifier: Mitigating PHP Object Injection Through Automatic Patch Generation

PFortifier: Mitigating PHP Object Injection Through Automati...

引用

IEEE Symposium on Security and Privacy

作者： Bo Pang Yiheng Zhang Mingzhe Gao Junzhe Zhang Ligeng Chen Mingxue Zhangt Gang Liang School of Cyber Science and Engineering Sichuan University Alibaba Cloud Computing National University of Singapore Honor Device Co. Ltd Nanjing University The State Key Laboratory of Blockchain and Data Security Zhejiang University

ISBN: (数字)9798331522360

ISBN: (纸本)9798331522377

PHP Object Injection (POI) vulnerabilities enable unexpected execution of class methods in PHP applications, resulting in various attacks. In the meanwhile, designing effective patches for POI vulnerabilities demands substantial engineering efforts. Existing research mostly focused on the detection of POI gadget chains, whereas the automatic patch generation remains an under-explored problem. In this work, we empirically study known gadget chains, and discover that adversaries usually construct gadget chains by diverging the execution to paths that developers never considered. The methods that get unexpectedly jump into (i.e., executed) are referred to as possible methods (PM). Based on the observation, we propose PFortifier, a framework for automatic POI patch generation. PFortifier operates in two stages: (i) the gadget chain detection phase, in which PFortifier simulates the execution of PHP applications, and detects gadget chains that pass attacker controlled objects to dangerous sinks, and (ii) the patch generation phase, in which PFortifier automatically generates POI patches by restricting PM jumps detected in the first phase. We evaluate PFortifier on 31 PHP applications and frameworks. The experiment results demonstrate the effectiveness of PFortifier: it generates precise patches for 52.53% of gadget chains, and suggests potential patches for 45.45% chains, resulting in a total chain coverage of 97.98%.

关键词： Privacy Static analysis Security

来源：评论

学校读者我要写书评

暂无评论

A multi-objective grey wolf optimizer for energy planning problem in smart home using renewable energy systems

引用

Sustainable Operations and Computers 2024年第1期5卷 88-101页

作者： Makhadmeh, Sharif Naser Al-Betar, Mohammed Azmi Al-Obeidat, Feras Alomari, Osama Ahmad Abasi, Ammar Kamal Tubishat, Mohammad Elgamal, Zenab Alomoush, Waleed Department of Data Science and Artificial Intelligence University of Petra Amman11196 Jordan College of Engineering and Information Technology Ajman University Ajman United Arab Emirates Department of Information Technology Al-Huson University College Al-Balqa Applied University P.O. Box 50 Al-Huson Irbid Jordan Department of Computer Science and Information Technology College of Engineering Abu Dhabi University Abu Dhabi United Arab Emirates College of Technological Innovation Zayed University Abu Dhabi United Arab Emirates School of Computing Skyline University College Sharjah United Arab Emirates School of Information Technology Skyline University College Sharjah P.O. Box 1797 United Arab Emirates Abu Dhabi United Arab Emirates

This paper presents the energy planning problem (EPP) as an optimization problem to find the optimal schedules to minimize energy consumption costs and demand and enhance users’ comfort levels. The grey wolf optimizer (GWO), One of the most powerful optimization methods, is adjusted and adapted to address EPP optimally and achieve its objectives efficiently. The GWO is adapted due to its high performance in addressing NP-complex hard problems like the EPP, where it contains efficient and dynamic parameters that enhance its exploration and exploitation capabilities, particularly for large search spaces. In addition, new energy and real-world resources based on solar renewable energy systems (RESs) are combined with the proposed GWO to enhance its performance and ensure the optimisation of EPP objectives. Furthermore, EPP is presented as a multi-objective planning problem to optimize all objectives simultaneously. To efficiently investigate the proposed method performance, the results obtained by the GWO with the RESs are compared in three stages: comparison with original methods without RESs, comparison with methods using RESs, and comparison with state-of-the-art. The obtained results proved the robust performance of the proposed method in handling EPP and optimizing its objectives. © 2024 The Author(s)

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization

arXiv

引用

arXiv 2023年

作者： Wang, Xiran Zhang, Jian Qi, Lei Shi, Yinghuan The State Key Laboratory for Novel Software Technology National Institute of Healthcare Data Science Nanjing University China The School of Computer Science and Engineering Southeast University China

Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains. However, most current methods do not account for a common realistic scenario where the source and target domains have different classes. To overcome this deficiency, open set domain generalization (OSDG) then emerges as a more practical setting to recognize unseen classes in unseen domains. An intuitive approach is to use multiple one-vs-all classifiers to define decision boundaries for each class and reject the outliers as unknown. However, the significant class imbalance between positive and negative samples often causes the boundaries biased towards positive ones, resulting in misclassification for known samples in the unseen target domain. In this paper, we propose a novel meta-learning-based framework called dualistic MEta-learning with joint DomaIn-Class matching (MEDIC), which considers gradient matching towards inter-domain and inter-class splits simultaneously to find a generalizable boundary balanced for all tasks. Experimental results demonstrate that MEDIC not only outperforms previous methods in open set scenarios, but also maintains competitive close set generalization ability at the same time. Our code is available at https://***/zzwdx/MEDIC. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Steganographic Distortion Function for Enhanced Images 19th

Steganographic Distortion Function for Enhanced Images

引用

19th International Workshop on Digital Forensics and Watermarking, IWDW 2020

作者： Wang, Zichi Feng, Guorui Zhang, Xinpeng Shanghai Institute for Advanced Communication and Data Science School of Communication and Information Engineering Shanghai University Shanghai200444 China

ISBN: (纸本)9783030694487

Contrast enhancement is widely used to improve the visual quality of images. This paper proposes a distortion function for steganography in enhanced images. The pixel prediction error and the cost of the pixel value itself are joint to fit the unique properties of enhanced image. Given a cover image, each pixel is predicted by its neighbors. The prediction error, which reflects the texture complexity, are combined with the cost of the pixel value itself to form the final distortion function. With the proposed distortion function, secret data can be embedded into the enhanced cover image with minimal image distortion using syndrome trellis coding (STC). As a result, less detectable artifacts left in the stego images, so that high undetectability is achieved. © 2021, Springer Nature Switzerland AG.

关键词： Steganography

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：