检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Shibuya, Tatsukichi Inoue, Nakamasa Kawakami, Rei Sato, Ikuro Department of Computer Science Institute of Science Tokyo Tokyo Japan Department of Systems and Control Engineering Institute of Science Tokyo Tokyo Japan Denso IT Laboratory Tokyo Japan

ISBN: (纸本)9798350368741

For deploying deep neural networks on edge devices with limited resources, binary neural networks (BNNs) have attracted significant attention, due to their computational and memory efficiency. However, once a neural network is binarized, finetuning it on edge devices becomes challenging because most conventional training algorithms for BNNs are designed for use on centralized servers and require storing real-valued parameters during training. To address this limitation, this paper introduces binary stochastic flip optimization (BinSFO), a novel training algorithm for BNNs. BinSFO employs a parameter update rule based on Boolean operations, eliminating the need to store real-valued parameters and thereby reducing memory requirements and computational overhead. In experiments, we demonstrated the effectiveness and memory efficiency of BinSFO in finetuning scenarios on six image classification datasets. BinSFO performed comparably to conventional training algorithms with a 70.7% smaller memory requirement. Code is released at https://***/TatsukichiShibuya/ICASSP2025_BinSFO. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamics of synthetic yeast chromosome evolution shaped by hierarchical chromatin organization

引用

National science Review 2023年第5期10卷 240-250页

作者： Sijie Zhou Yi Wu Yu Zhao Zhen Zhang Limin Jiang Lin Liu Yan Zhang Jijun Tang Ying-Jin Yuan Frontiers Science Center for Synthetic Biology (Ministry of Education) Tianjin University Key Laboratory of Systems Bioengineering(Ministry of Education) School of Chemical Engineering and TechnologyTianjin University Institute for Systems Genetics NYU Langone Health School of Computer Science and Technology College of Intelligence and ComputingTianjin University Epigenetic Group Frasergen Bioinformatics Co.Ltd. Department of Computer Science University of South Carolina

Synthetic genome evolution provides a dynamic approach for systematically and straightforwardly exploring evolutionary *** Chromosome Rearrangement and Modification by LoxP-mediated Evolution(SCRaMbLE) is an evolutionary system intrinsic to the synthetic yeast genome that can rapidly drive structural ***,we detect over 260 000 rearrangement events after the SCRaMbLEing of a yeast strain harboring 5.5 synthetic yeast chromosomes(synⅡ,synⅢ,synⅤ,circular synⅥ,synⅨR and synⅩ).Remarkably,we find that the rearrangement events exhibit a specific landscape of *** further reveal that the landscape is shaped by the combined effects of chromatin accessibili and spatial contact *** rearrangements tend to occur in 3D spatially proximal and chromatin-accessible *** enormous numbers of rearrangements mediated by SCRaMbLE provide a driving force to potentiate directed genome evolution,and the investigation of the rearrangement landscape offers mechanistic insights into the dynamics of genome evolution.

关键词： synthetic biology genome rearrangement hierarchical chromatin organization synthetic yeast genome SCRaMbLE Saccharomyces cerevisiae

来源：评论

学校读者我要写书评

暂无评论

Enhancing Self-regulated Learning Through an Emotional Chatbot: A Conceptual Framework 9th

Enhancing Self-regulated Learning Through an Emotional Chatb...

引用

9th International Conference on Smart City Applications, SCA 2024

作者： El Mourabit, Imane Jai Andaloussi, Said Ouchetto, Ouail Miyara, Mounia Computer Science and Systems Laboratory Department of Mathematics and Computer Sciences Faculty of Sciences Ain Chock Hassan II University of Casablanca Casablanca Morocco

ISBN: (纸本)9783031886522

Artificial Intelligence (AI) chatbots play an important role in modernizing education, particularly e-learning platforms by acting as intelligent tools to address issues such as disengagement and dropout rates. AI chatbots are also used to captivate students through engaging and enjoyable learning activities. These chatbots can enhance the pedagogical concept of Self-Regulated Learning (SRL) by providing personalized support and feedback to students. This work explores how AI chatbots might increase students’ SRL skills and foster successful learning outcomes in e-learning environments. Our proposed conceptual framework aims to link the AI chatbots (technological side) and self-regulated learning (pedagogical side) using the power of academic emotions. In the forethought phase of SRL, our AI chatbot will guide students in setting short-term goals while detecting their initial motivation and then monitor students in the following phases of the SRL process. The framework highlights how AI chatbots using academic emotions can be used to support learning needs and will serve as a roadmap for future theory development and empirical investigation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-rank Decomposition 24

Decoupling General and Personalized Knowledge in Federated L...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wu, Xinghao Liu, Xuefeng Niu, Jianwei Wang, Haolin Tang, Shaojie Zhu, Guogang Su, Hao State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Department of Management Science and Systems University at Buffalo BuffaloNY United States School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9798400706868

To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on collaboration if not removed. Existing PFL methods primarily adopt a parameter partitioning approach, where the parameters of a model are designated as one of two types: parameters shared with other clients to extract general knowledge and parameters retained locally to learn client-specific knowledge. However, as these two types of parameters are put together like a jigsaw puzzle into a single model during the training process, each parameter may simultaneously absorb both general and client-specific knowledge, thus struggling to separate the two types of knowledge effectively. In this paper, we introduce FedDecomp, a simple but effective PFL paradigm that employs parameter additive decomposition to address this issue. Instead of assigning each parameter of a model as either a shared or personalized one, FedDecomp decomposes each parameter into the sum of two parameters: a shared one and a personalized one, thus achieving a more thorough decoupling of shared and personalized knowledge compared to the parameter partitioning method. In addition, as we find that retaining local knowledge of specific clients requires much lower model capacity compared with general knowledge across all clients, we let the matrix containing personalized parameters be low rank during the training process. Moreover, a new alternating training strategy is proposed to further improve the performance. Experimental results across multiple datasets and varying degrees of data heterogeneity demonstrate that FedDecomp outperforms state-of-the-art methods up to 4.9%. The code is available at https://***/XinghaoWu/FedDecomp © 2024 ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Actor-Critic Algorithm based Autonomous Lane Change Decisions in Static Environments 6

Deep Reinforcement Learning Actor-Critic Algorithm based Aut...

引用

6th International Conference on Intelligent Computing in Data sciences, ICDS 2024

作者： Safae, Belkhyr Jaouad, Boumhidi Nikolov Nikola, S. University Sidi Mohamed Ben LISAC Laboratory Computer Science Departement Faculty of Science Dhar EI Mahraz Abdellah Fez Morocco University of Limerick Department of Computer Science and Information Systems Limerick Ireland

ISBN: (纸本)9798350351200

Deep Reinforcement Learning (DRL) has emerged as a pivotal technology in modern transportation systems, offering considerable potential to enhance driving safety and optimize performance. This study underscores the significance of DRL in autonomous driving (AD) and introduces the Advantage Actor-Critic (A2C) approach for lane change decision-making. A2C, representing policy-based methods, is compared with the Prioritized Replay Deep Q-Network (PRDQN), a value-based approach previously used in similar scenarios. Both approaches were evaluated using the CARLA (Car Learning to Act) simulation environment, focusing on static obstacle scenarios. The comparative analysis aims to assess the performance differences between A2C and PRDQN, highlighting the effectiveness of A2C in improving decision-making accuracy, safety, and adaptability. The results demonstrate the superior performance of A2C in improving safety and decision-making within autonomous driving systems. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Prescribed-Time Nash Equilibrium Seeking for Pursuit-Evasion Game

引用

IEEE/CAA Journal of Automatica Sinica 2024年第6期11卷 1518-1520页

作者： Lei Xue Jianfeng Ye Yongbao Wu Jian Liu D.C.Wunsch Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationNanjing 210096 School of Automation Southeast UniversityNanjing 210096China Department of Electrical and Computer Engineering Missouri University of Science and TechnologyRollaMO 65409 USA IEEE

Dear Editor,This letter is concerned with prescribed-time Nash equilibrium(PTNE)seeking problem in a pursuit-evasion game(PEG)involving agents with second-order *** order to achieve the prior-given and user-defined convergence time for the PEG,a PTNE seeking algorithm has been developed to facilitate collaboration among multiple pursuers for capturing the evader without the need for any global ***,it is theoretically proved that the prescribedtime convergence of the designed algorithm for achieving Nash equilibrium of ***,the effectiveness of the PTNE method was validated by numerical simulation results.A PEG consists of two groups of agents:evaders and *** pursuers aim to capture the evaders through cooperative efforts,while the evaders strive to evade *** is a classic noncooperative *** has attracted plenty of attention due to its wide application scenarios,such as smart grids[1],formation control[2],[3],and spacecraft rendezvous[4].It is noteworthy that most previous research on seeking the Nash equilibrium of the game,where no agent has an incentive to change its actions,has focused on asymptotic and exponential convergence[5]-[7].

关键词： seeking prescribed convergence

来源：评论

学校读者我要写书评

暂无评论

DualFed: Enjoying both Generalization and Personalization in Federated Learning via Hierachical Representations 24

DualFed: Enjoying both Generalization and Personalization in...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhu, Guogang Liu, Xuefeng Niu, Jianwei Tang, Shaojie Wu, Xinghao Zhang, Jiayuan State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Department of Management Science and Systems University at Buffalo BuffaloNY United States

ISBN: (纸本)9798400706868

In personalized federated learning (PFL), it is widely recognized that achieving both high model generalization and effective personalization poses a significant challenge due to their conflicting nature. As a result, existing PFL methods can only manage a trade-off between these two objectives. This raises an interesting question: Is it feasible to develop a model capable of achieving both objectives simultaneously? Our paper presents an affirmative answer, and the key lies in the observation that deep models inherently exhibit hierarchical architectures, which produce representations with various levels of generalization and personalization at different stages. A straightforward approach stemming from this observation is to select multiple representations from these layers and combine them to concurrently achieve generalization and personalization. However, the number of candidate representations is commonly huge, which makes this method infeasible due to high computational costs. To address this problem, we propose DualFed, a new method that can directly yield dual representations correspond to generalization and personalization respectively, thereby simplifying the optimization task. Specifically, DualFed inserts a personalized projection network between the encoder and classifier. The pre-projection representations are able to capture generalized information shareable across clients, and the post-projection representations are effective to capture task-specific information on local clients. This design minimizes the mutual interference between generalization and personalization, thereby achieving a win-win situation. Extensive experiments show that DualFed can outperform other FL methods. Code is available at https://***/GuogangZhu/DualFed. © 2024 ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

ROBUSTIFYING AND BOOSTING TRAINING-FREE NEURAL ARCHITECTURE SEARCH 12

ROBUSTIFYING AND BOOSTING TRAINING-FREE NEURAL ARCHITECTURE ...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： He, Zhenfeng Shu, Yao Dai, Zhongxiang Low, Bryan Kian Hsiang Department of Computer Science National University of Singapore Singapore China Laboratory for Information and Decision Systems Massachusetts Institute of Technology United States

Neural architecture search (NAS) has become a key component of AutoML and a standard tool to automate the design of deep neural networks. Recently, training-free NAS as an emerging paradigm has successfully reduced the search costs of standard training-based NAS by estimating the true architecture performance with only training-free metrics. Nevertheless, the estimation ability of these metrics typically varies across different tasks, making it challenging to achieve robust and consistently good search performance on diverse tasks with only a single training-free metric. Meanwhile, the estimation gap between training-free metrics and the true architecture performances limits training-free NAS to achieve superior performance. To address these challenges, we propose the robustifying and boosting training-free NAS (RoBoT) algorithm which (a) employs the optimized combination of existing training-free metrics explored from Bayesian optimization to develop a robust and consistently better-performing metric on diverse tasks, and (b) applies greedy search, i.e., the exploitation, on the newly developed metric to bridge the aforementioned gap and consequently to boost the search performance of standard training-free NAS further. Remarkably, the expected performance of our RoBoT can be theoretically guaranteed, which improves over the existing training-free NAS under mild conditions with additional interesting insights. Our extensive experiments on various NAS benchmark tasks yield substantial empirical evidence to support our theoretical results. Our code has been made publicly available at https://***/hzf1174/RoBoT. © 2024 12th International Conference on Learning Representations, ICLR 2024. 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

Latest Innovations in Intelligent Network-on-Chip Architectures: A Systematic Review 17

Latest Innovations in Intelligent Network-on-Chip Architectu...

引用

17th IEEE/ACM International Workshop on Network on Chip Architectures, NoCArc 2024

作者： Kakoulli, Elena Neapolis University Pafos Intelligent Systems Laboratory Department of Computer Science Pafos Cyprus Cyprus University of Technology Electrical Engineering and Computer Engineering and Informatics Limassol Cyprus

ISBN: (纸本)9798331506421

This review investigates the latest advancements in intelligent Network-on-Chip (NoC) architectures, focusing on innovations from 2022 to 2024. The integration of Artificial Intelligence (AI) and Machine Learning (ML) into NoC designs has driven significant improvements in performance, scalability, energy efficiency, and security. Key contributions include AI/ML-driven techniques to optimize routing, reduce latency, manage power consumption, and enhancing security against emerging threats. Despite these advancements, challenges such as computational overhead and integration complexities remain. This review consolidates these findings, addresses existing challenges, and proposes future research directions to further leverage AI and ML for developing robust and adaptable NoC architectures. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Robust Security Detection Strategy for Next Generation IoT Networks

引用

computers, Materials & Continua 2025年第1期82卷 443-466页

作者： Hafida Assmi Azidine Guezzaz Said Benkirane Mourade Azrour Said Jabbour Nisreen Innab Abdulatif Alabdulatif Technology Higher School Essaouira Cadi Ayyad UniversityEssaouira44000Morocco IMIA Laboratory MSIA TeamFaculty of Sciences and TechniquesMoulay Ismail University of MeknesErrachidia50050Morocco CRIL-CNRS Artois UniversityLens62300France Department of Computer Science and Information Systems College of Applied SciencesAlMaarefa UniversityDiriyahRiyadh13713Saudi Arabia Department of Computer Science College of ComputerQassim UniversityBuraydah52571Saudi Arabia

Internet of Things(IoT)refers to the infrastructures that connect smart devices to the Internet,operating *** connectivitymakes it possible to harvest vast quantities of data,creating new opportunities for the emergence of unprecedented *** ensure IoT securit,various approaches have been implemented,such as authentication,encoding,as well as devices to guarantee data integrity and *** these approaches,Intrusion Detection systems(IDS)is an actual security solution,whose performance can be enhanced by integrating various algorithms,including Machine Learning(ML)and Deep Learning(DL),enabling proactive and accurate detection of *** study proposes to optimize the performance of network IDS using an ensemble learning method based on a voting classification *** combining the strengths of three powerful algorithms,Random Forest(RF),K-Nearest Neighbors(KNN),and Support Vector Machine(SVM)to detect both normal behavior and different categories of *** analysis focuses primarily on the NSL-KDD dataset,while also integrating the recent Edge-IIoT dataset,tailored to industrial IoT *** results show significant enhancements on the Edge-IIoT and NSL-KDD datasets,reaching accuracy levels between 72%to 99%,with precision between 87%and 99%,while recall values and F1-scores are also between 72%and 99%,for both normal and attack *** the promising results of this study,it suffers from certain limitations,notably the use of specific datasets and the lack of evaluations in a variety of *** work could include applying this model to various datasets and evaluating more advanced ensemble strategies,with the aim of further enhancing the effectiveness of IDS.

关键词： IoT security intrusion detection RF KNN SVM EL NSL-KDD Edge-IIoT

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：