检索结果-内蒙古大学图书馆

60th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2024

作者： Lee, Dongmin Makur, Anuran Purdue University Department of Computer Science West LafayetteIN United States School of Electrical and Computer Engineering Purdue University West LafayetteIN United States

ISBN: (纸本)9798331541033

Contraction coefficients for Kullback-Leibler (KL) divergence are channel-dependent constants that are used to sharpen data processing inequalities for KL divergence into strong data processing inequalities. In this work, we present a method to analytically compute the KL contraction coefficients of product q-ary symmetric channels. Although such contraction coefficients have many applications in information theory as well as probability and statistics more broadly, deriving exact values is considered to be challenging for complex channels such as product channels. While recent discoveries have reduced the search space of the optimization problems defining contraction coefficients significantly, the problem is still far from trivial. We find that the symmetry inherent in channels such as the q-ary symmetric channel allows for further simplification, making an exact closed-form expression for contraction coefficients for KL divergence possible to derive. We begin by obtaining the KL contraction coefficients of product binary symmetric channels, and then generalize our results to larger alphabets. Our methods are not specific to product q-ary symmetric channels and can be used for wider classes of channels that satisfy certain symmetry properties. © 2024 IEEE.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Model-to-Circuit Cross-Approximation for Printed Machine Learning Classifiers

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2023年第11期42卷 3532-3544页

作者： Armeniakos, Giorgos Zervakis, Georgios Soudris, Dimitrios Tahoori, Mehdi B. Henkel, Jorg Karlsruhe Institute of Technology Karlsruhe76131 Germany National Technical University of Athens School of Electrical and Computer Engineering Athens15780 Greece University of Patras Computer Engineering and Informatics Department Patras26504 Greece Karlsruhe Institute of Technology Department of Computer Science Karlsruhe76131 Germany

Printed electronics (PEs) promises on-demand fabrication, low nonrecurring engineering costs, and subcent fabrication costs. It also allows for high customization that would be infeasible in silicon, and bespoke architectures prevail to improve the efficiency of emerging PE machine learning (ML) applications. Nevertheless, large feature sizes in PE prohibit the realization of complex ML models in PE, even with bespoke architectures. In this work, we present an automated, cross-layer approximation framework tailored to bespoke architectures that enable complex ML models, such as multilayer perceptrons (MLPs) and support vector machines (SVMs), in PE. Our framework adopts cooperatively a hardware-driven coefficient approximation of the ML model at algorithmic level, a netlist pruning at logic level, and a voltage overscaling at the circuit level. Extensive experimental evaluation on 12 MLPs and 12 SVMs and more than 6000 approximate and exact designs demonstrates that our model-to-circuit cross-approximation delivers power and area optimal designs that, compared to the state-of-the-art exact designs, feature on average 51% and 66% area and power reduction, respectively, for less than 5% accuracy loss. Finally, we demonstrate that our framework enables 80% of the examined classifiers to be battery-powered with almost identical accuracy with the exact designs, paving thus the way toward smart complex printed applications. © 1982-2012 IEEE.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Efficient Meeting Insights: NLP-Enhanced Summarization of Voice and Text 15

Efficient Meeting Insights: NLP-Enhanced Summarization of Vo...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Brahmachari, K. Sankar Hanumesh, Mangaluru Anitha, G. Pattanaik, Balachandra Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Tamil Nadu Chennai India Wollega University School of Electrical Computer Engineering Nekemte Ethiopia

ISBN: (纸本)9798350370249

In order to improve meeting efficiency in the ever-changing workplace, research has mostly focused on sophisticated text summarization techniques such as machine learning, hybrid, semantic, and graph-based methods. These approaches have shown efficient in extracting key information from lengthy talks, hence dramatically improving decision-making and knowledge retention. However, their potential has been somewhat limited by a major concentration on processing material in a single language, which ignores the complex, multilingual environment of modern global enterprises. Our most recent research project tries to overcome this gap by combining these various summarizing approaches into acomplete, language-neutral ***, to address the specific difficulty of long meetings, when extracting insights might be especially difficult for those who are not there, we propose using the Longformer encoder-decoder paradigm. This methodology excels at distilling lengthy talks into digestible summaries, regardless of the original language, ensuring that critical insights are easily accessible to anybody, hence increasing inclusion and comprehension across multinational teams. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Robust Monocular Camera-Based Localization in Industrial Environments

Robust Monocular Camera-Based Localization in Industrial Env...

引用

2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024

作者： Won, Yungu Choi, Yein Ryu, Hwangryol Moon, Youngmin Kwon, Kihoon Hwang, Sung Soo Handong Global University Dept. of Computer Science and Electrical Engineering Pohang Korea Republic of Research Institute of Industrial Science & Technology Smart Engineering Research Laboratory Pohang Korea Republic of School of Computer Science and Electrical Engineering Handong Global University Pohang Korea Republic of

ISBN: (纸本)9798331530839

This paper proposes a camera-based system for robust localization of workers or robots in large-scale factories and industrial sites. The system is designed with the convenience and efficiency of workers in mind, providing stable tracking capabilities. To achieve this, a monocular camera is attached to a safety helmet, enabling localization without restricting the worker's range of motion. Additionally, by combining Visual Simultaneous Localization and Mapping and Visual Place Recognition, the system tracks the location of workers or robots while minimizing tracking loss, ensuring consistent localization. Our methodology has enhanced the accuracy and reliability of position estimation by approximately 46.0%. By accurately identifying the location of workers or robots, the system aims to prevent accidents and ensure swift responses in emergency situations. © 2024 IEEE.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Minimizing Negative Side Effects in Cooperative Multi-Agent Systems Using Distributed Coordination 37

Minimizing Negative Side Effects in Cooperative Multi-Agent ...

引用

37th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2024

作者： Choudhury, Moumita Saisubramanian, Sandhya Zhang, Hao Zilberstein, Shlomo College of Information and Computer Sciences University of Massachusetts Amherst United States School of Electrical Engineering and Computer Science Oregon State University United States

Autonomous agents operating in real-world environments frequently encounter undesirable outcomes or negative side effects (NSEs) when working collaboratively alongside other agents. Even when agents can execute their primary task optimally when operating in isolation, their training may not account for potential negative interactions that arise in the presence of other agents. We frame the challenge of minimizing NSEs as a lexicographic decentralized Markov decision process in which we assume independence of rewards and transitions with respect to the primary assigned tasks, but recognize that addressing negative side effects creates a form of dependence among the agents. We present a lexicographic Q-learning approach to mitigate the NSEs using human feedback models while maintaining near-optimality with respect to the assigned tasks—up to some given slack. Our empirical evaluation across two domains demonstrates that our collaborative approach effectively mitigates NSEs, outperforming non-collaborative methods. Copyright © 2024 by the authors.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

Getting GPT to answer like me 37

Getting GPT to answer like me

引用

37th International BCS Human-computer Interaction Conference, BCS HCI 2024

作者： O’Neill, Ian School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast Computer Science Building BelfastBT9 5BN United Kingdom

This paper provides insights into the development of a prototype tutorial chatbot, using Azure AI and GPT-4. The prototype system answers and poses questions in the manner of a module lecturer in tutorials – able to vary content and phrasing according to circumstance. Use cases in the Unified Modeling Language (UML) are the topic of the tutorial. The system asks questions about and explains core concepts, using the rules of thumb and simplifications that the author/module lecturer would use. By assimilating or ‘ingesting’ natural language instructions and core documents (one of which represents basic domain knowledge while others represent the author’s own presentational tips and hints) the system’s dialogue style comes to resemble that of the author. While the system described here remains a prototype which will require further testing, the results are very encouraging. The paper will be of interest to other educators wishing to create a chatbot that can answer recurrent enquiries about, and reinforce basic concepts in, an academic specialism. © O’Neill.

关键词： Unified Modeling Language

来源：评论

学校读者我要写书评

暂无评论

Fairness in Machine Learning for Cybersecurity: Enhancing Trust Through Feature Importance and SHAP Analysis 4

Fairness in Machine Learning for Cybersecurity: Enhancing Tr...

引用

4th International Conference on electrical, computer, Communications and Mechatronics engineering, ICECCME 2024

作者： Heydari, Vahid Nyarko, Kofi Morgan State University Computer Science Department Baltimore United States Morgan State University Electrical and Computer Engineering Department Baltimore United States

ISBN: (纸本)9798350391183

This paper addresses the issue of fairness in machine learning (ML) models within the cybersecurity domain, focusing on the interpretability and trustworthiness of model decisions. By applying feature importance analysis and SHAP (SHapley Additive exPlanations) values to a ransom ware detection dataset, we identify and mitigate unintended biases that can compromise the security of these models. The findings reveal that certain features, such as file names and DLL characteristics, disproportionately influence model predictions, creating vulnerabilities that attackers can exploit. Furthermore, the potential of Generative Adversarial Networks (GANs) to strengthen model robustness against adversarial attacks is explored. The approach presented offers notable improvements in the transparency and reliability of ML models within the cybersecurity domain. These insights provide practical guidelines for researchers to develop fairer and more resilient ML models for cybersecurity applications. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Adaptive Game Design Using Machine Learning Techniques: A Survey

Adaptive Game Design Using Machine Learning Techniques: A Su...

引用

2024 IEEE International Conference on Internet of Things and Intelligence Systems, IoTaIS 2024

作者： Hossan, Md Mosharaf Fouda, Mostafa M. Eishita, Farjana Z. Department of Computer Science Idaho State University Pocatello United States Department of Electrical and Computer Engineering Idaho State University Pocatello United States

ISBN: (纸本)9798331521219

Adaptive game design is a dynamic gamification approach that changes game elements such as challenges, feedback mechanisms, and rewards based on players’ preferences, behaviors, and needs. It is an emerging research field that aims to improve classic gamification techniques by adapting a game environment to meet the particular needs of various users and contexts. Machine learning (ML) techniques have the ability to predict future actions based on historical data to progress toward an ideal outcome. In digital gaming, adaptation of different gaming elements such as levels, difficulty, and feedback to match players’ skills is a fundamental requirement for an enjoyable experience. In this scenario, ML techniques can come into play. These techniques can help to advance the enjoyment of the gameplay toward players’ maximum satisfaction and engagement by anticipating the necessary changes in the game based on their previous behaviors. In this paper, we have conducted a systematic review of 17 papers to investigate the game balancing technology adopted recently. The fundamental goal of this survey is to provide a comprehensive overview of the latest developments in game balancing technologies that use ML techniques. ©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

Surface phase diagram of CsSnI3 from first-principles calculations

引用

Physical Review Materials 2024年第9期8卷 093401页

作者： Kejia Li Chadawan Khamdang Mengen Wang Department of Electrical and Computer Engineering Materials Science and Engineering Program

CsSnI3 is widely studied as an environmentally friendly Pb-free perovskite material for optoelectronic device applications. To further improve material and device performance, it is important to understand the surface structures of CsSnI3. We generate surface structures with various stoichiometries, perform density functional theory calculations to create phase diagrams of the CsSnI3 (001), (110), and (100) surfaces, and determine the most stable surfaces under a wide range of Cs, Sn, and I chemical potentials. Under I-rich conditions, surfaces with Cs vacancies are stable, which lead to partially occupied surface states above the valence band maximum. Under I-poor conditions, we find the stoichiometric (100) surface to be stable under a wide region of the phase diagram, which does not have any surface states and can contribute to long charge-carrier lifetimes. Consequently, the I-poor (Sn-rich) conditions will be more beneficial to improve the device performance.

关键词： Electronic structure Surface reconstruction Surface states Perovskites Semiconductors Density functional theory

来源：评论

学校读者我要写书评

暂无评论

Vision-Language Feature Refinement for Zero-Shot Object Counting 9

Vision-Language Feature Refinement for Zero-Shot Object Coun...

引用

9th International Conference on Frontiers of Signal Processing, ICFSP 2024

作者： Haque Jiban, Md Jibanul Mahalanobis, Abhijit Da Vitoria Lobo, Niels University of Central Florida Department of Computer Science OrlandoFL United States University of Arizona Electrical and Computer Engineering TucsonAZ United States

ISBN: (纸本)9798350353235

Large-scale vision-language pretraining has revolutionized zero-shot learning tasks by enabling models to effectively handle novel object categories using rich, generalized visual-language associations. However, it is challenging to use for dense tasks like zero-shot object counting due to their inherent difficulty in accurately localizing and quantifying a large number of unseen and diverse objects in complex images. To address this, we utilize a cross-modal encoder to learn joint representations from both modalities at the pixel level. We also introduce a refinement process that further processes the visual features to improve localization and capture multi-scale contextual information for robust counting. We perform extensive experiments on FSC-147 to show state-of-the-art performance on zero-shot counting and demonstrate improved cross-data generalization on the CARPK dataset. © 2024 IEEE.

关键词： Zero-shot learning

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：