检索结果-内蒙古大学图书馆

Unlearning Recently Learned Data to Preserve Historical Learning for Dynamic Data Stream Classification

Chinese Journal of Electronics 2025年第3期34卷 849-860页

作者： Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin 541004 China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin 541004 China School of Municipal and Surveying Engineering Hunan City University Yiyang 413000 China

At present, dynamic data stream classification has achieved many successful results through concept drift detection and ensemble learning. However, generally, due to delay in concept drift detection, the active classifier may further learn data belonging to a new concept. This will ultimately degrade the generalization capability of this active classifier on its corresponding concept. Thus, how can a classifier corresponding to one concept unlearns the learned data belonging to another concept? Two unlearning algorithms are proposed to address this problem. The first one based on the passive-aggressive (PA) algorithm adopts the least squares method to reversely update the already-trained model, achieving the effect of approximately unlearning, while another based on a modified PA algorithm achieves complete unlearning by modifying the loss function of the PA algorithm. The comprehensive experiments illustrated the effectiveness of these proposed methods.

关键词： Data stream Machine unlearning Concept drift Online learning

来源：评论

学校读者我要写书评

暂无评论

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration 38

Speculative Decoding with CTC-based Draft Model for LLM Infe...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Wen, Zhuofan Gui, Shangtong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Al Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed. © 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

A Novel NASICON‑Type Na_(3.5)MnCr_(0.5)Ti_(0.5)(PO_(4))_(3)Nanofiber with Multi‑electron Reaction for High‑Performance Sodium‑Ion Batteries

引用

Advanced Fiber Materials 2024年第2期6卷 561-569页

作者： Ting Zhu Wei Liu Xiaobin Liao Mengyao Wang Hao Fan Zihe Wei Congcong Cai Liyan Yang Mufang Li Dong Wang Ping Hu Xuanpeng Wang Key Laboratory of Textile Fiber and Products Ministry of EducationHubei International Scientific and Technological Cooperation Base of Intelligent TextileMaterials&ApplicationWuhan Textile UniversityWuhan 430200China Hubei Key Laboratory of Micro‑Nanoelectronic Materials and Devices School of MicroelectronicsHubei UniversityWuhan 430062China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Wuhan University of TechnologyWuhan 430070China Department of Physical Science&Technology School of ScienceWuhan University of TechnologyWuhan 430070China Hubei Longzhong Laboratory Wuhan University of Technology(Xiangyang Demonstration Zone)Xiangyang 441000China

Sodium superionic conductors(NASICONs)show significant promise for application in the development of cathodes for sodium-ion batteries(SIBs).However,it remains a major challenge to develop the desired multi-electron reaction cathode with a high specific capacity and energy ***,we report a novel NASICON-type Na_(3.5)MnCr_(0.5)Ti_(0.5)(PO_(4))_(3)cathode obtained by combining electrospinning and stepwise sintering *** cathode exhibits a high discharge capacity of 160.4 mAh g^(−1)and operates at a considerable medium voltage of 3.2 *** Na_(3.5)MnCr_(0.5)Ti_(0.5)(PO_(4))_(3)cathode undergoes a multi-electron redox reaction involving the Cr^(3+/4+)(4.40/4.31 V ***/Na^(+)),Mn^(3+/4+)(4.18/4.03 V),Mn^(2+/3+)(3.74/3.41 V),and Ti^(3+/4+)(2.04/2.14 V)redox *** redox reaction enables a three-electron transfer during the Na+intercalation/de-intercalation *** a result,the Na_(3.5)MnCr_(0.5)Ti_(0.5)(PO_(4))_(3)demonstrates a significant enhancement in energy density,surpassing other recently reported SIB *** highly reversible structure evolution and small volume changes during cycling were demonstrated with in-situ X-ray diffraction,ensuring outstanding cyclability with 77%capacity retention after 500 ***,a NMCTP@C//Sb@C full battery was fabricated,which delivered a high energy density of 421 Wh kg−1 and exhibited good cyclability with 75.7%capacity retention after 100 *** rational design of composition regulation with multi-metal ion substitution holds the potential to unlock new possibilities in achieving high-performance SIBs.

关键词： Sodium-ion battery NASICON structure Na_(3.5)MnCr_(0.5)Ti_(0.5)(PO_(4))_(3)nanofiber Ex/in-situ characterization Multi-electron reaction

来源：评论

学校读者我要写书评

暂无评论

Blind Image Deconvolution Based on Adaptive Euler’s Elastica Regularization

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2024年第1期51卷 32-38页

作者： Song, Xiuzheng Zhang, Jun Lu, Jingjing Rao, Sanping College of Science Nanchang Institute of Technology Jiangxi Nanchang330099 China College of Science Nanchang Institute of Technology Jiangxi Nanchang330099 China Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang Institute of Technology Jiangxi Nanchang330099 China College of Science Nanchang Institute of Technology Jiangxi Nanchang330099 China

—Blind image deconvolution has garnered significant attention in the realm of image processing. Among existing blind deconvolution models, the adaptive weighted total variation-based model can better recover local image features. However, this model may give rise to undesirable staircase effects. In contrast, when considering non-blind deconvolution, a model that uses adaptive Euler’s elastica (AEE) regularization can reduce the appearance of staircase effects and better maintain image local features. Inspired by the successful application of the AEE regularization in non-blind deconvolution, we propose an AEE model for blind image deconvolution. This novel model can preserve image features in smooth regions and restore local characteristics of the image. In addition, an efficient alternating direction method of multipliers is designed to address this non-convex model. Experimental results illustrate the superiority of the proposed method compared with other related blind deconvolution methods. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for State of Health Estimation and Remaining Useful Life Prediction of Supercapacitors Using an Improved Honey Badger Algorithm Assisted Hybrid Neural Network

引用

Protection and Control of Modern Power Systems 2024年第6期9卷 1-18页

作者： Zhenxiao Yi Shi Wang Zhaoting Li Licheng Wang Kai Wang the School of Electrical Engineering Qingdao UniversityQingdao 266071Chinaand the State Key Laboratory of Reliability and Intelligence of Electrical EquipmentHebei University of TechnologyTianjin 300130China the Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China the School of Engineering Brown UniversityProvidenceRhode Island 02912USA the School of Information Engineering Zhejiang University of TechnologyHangzhou 310014China the School of Electrical Engineering Qingdao UniversityQingdao 266071China

Supercapacitors(SCs)are widely recognized as excellent clean energy storage *** state of health(SOH)estimation and remaining useful life(RUL)prediction are essential for ensuring their safe and reliable *** paper introduces a novel method for SOH estimation and RUL prediction,based on a hybrid neural network optimized by an improved honey badger algorithm(HBA).The method combines the advantages of convolutional neural network(CNN)and bidirectional long-short-term memory(BiLSTM)neural *** HBA optimizes the hyperparameters of the hybrid neural *** CNN automatically extracts deep features from time series data and reduces dimensionality,which are then used as input for the ***,recurrent dropout is introduced in the recurrent layer to reduce overfitting and facilitate the learning *** approach not only improves the accuracy of estimates and forecasts but also significantly reduces data processing *** under different working conditions are used to validate the proposed *** results show that the proposed hybrid model effectively extracts features,enriches local details,and enhances global perception *** proposed hybrid model outperforms single models,reducing the root mean square error to below 1%,and offers higher prediction accuracy and robustness compared to other methods.

关键词： Supercapacitors state of health remaining useful life honey badger algorithm recurrent dropout.

来源：评论

学校读者我要写书评

暂无评论

Nonautonomous Breather and Rogue Wave in Spinor Bose–Einstein Condensates with Space-Time Modulated Potentials

引用

Chinese Physics Letters 2023年第4期40卷 6-10页

作者：丁崔崔周勤徐四六 Houria Triki Mohammad Mirzazadeh 刘文军 Research Group of Nonlinear Optical Science and Technology School of Mathematical and Physical SciencesWuhan Textile UniversityWuhan 430200China State Key Laboratory of New Textile Materials and Advanced Processing Technologies Wuhan Textile UniversityWuhan 430200China School of Biomedical Engineering and Medical Imaging Xianning Medical CollegeHubei University of Science and TechnologyXianning 437100China Radiation Physics Laboratory Department of PhysicsFaculty of SciencesBadji Mokhtar UniversityP.O.Box 1223000 AnnabaAlgeria Department of Engineering Sciences Faculty of Technology and EngineeringEast of GuilanUniversity of GuilanRudsar-VajargahIran State Key Laboratory of Information Photonics and Optical Communications School of ScienceBeijing University of Posts and TelecommunicationsBeijing 100876China

To study controlled evolution of nonautonomous matter-wave breathers and rogue waves in spinor Bose–Einstein condensates with spatiotemporal modulation,we focus on a system of three coupled Gross–Pitaevskii equations with spacetime-dependent external potentials and temporally modulated gain-loss *** different external potentials and gain-loss distributions,various solutions for controlled nonautonomous matterwave breathers and rogue waves are derived by the Darboux transformation method,such as breathers and rogue waves on arched and constant backgrounds which have the periodic and parabolic *** of the gain-loss distribution and linear potential on the breathers and rogue waves are *** two-breathers on the arched and constant backgrounds are also derived.

关键词： Einstein Nonautonomous parabolic

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Warning Signs for Vehicles Based on Automatic Navigation Algorithms 1

引用

13th International Conference on Computer Engineering and Networks, CENet 2023

作者： Wang, Fangyan Jiao, Ge Lu, Jinjia Yuan, Yiping College of Computer Science and Technology Hengyang Normal University Hunan Hengyang421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hunan Hengyang421002 China

ISBN: (数字)9789819992393

ISBN: (纸本)9789819992386

Traditional warning signs use human retrograde placement;there are problems such as short warning distances, imprecise placement positions, and difficult positioning of accident points. According to statistics, the user's reaction time after facing a car accident is generally 1.05–1.28 s, and the reaction time to light is 0.225 s. The reaction time for the user to deal with a car accident independently is completely insufficient, and these reasons are the main reasons for secondary traffic accidents. In order to solve this social pain point, we designed a new intelligent triangle warning sign. The intelligent warning sign is installed with an intelligent base at the bottom, and it gets the traffic accident point precisely located when the intelligent warning sign is working, and the system gets the vehicle accident point and reminds the vehicles behind to pay attention to avoid, realizing the three-way interconnection of drivers and passengers, traffic control departments, and the personnel of the vehicles behind, and using the automatic navigation algorithm to realize the automatic navigation of the warning sign to protect the safety of drivers and passengers. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Specific Ion Effects on the Enzymatic Degradation of Polyester Films

引用

Chinese Journal of Polymer Science 2023年第4期41卷 476-482,I0005页

作者： Jian Zhang Jie Zhu Zan Hua Guang-Ming Liu Department of Chemical Physics Key Laboratory of Surface and Interface Chemistry and Energy Catalysis of Anhui Higher Education InstitutesUniversity of Science and Technology of ChinaHefei230026China Key Laboratory of Yarn Materials Forming and Composite Processing Technology of Zhejiang Province College of Material and Textile EngineeringJiaxing UniversityJiaxing314001China Biomass Molecular Engineering Center and Department of Materials Science and Engineering School of Forestry and Landscape ArchitectureAnhui Agricultural UniversityHefei230036China

Soil environment on earth contains a variety of ions,which are expected to play a vital role in the biodegradation of plastics discarded in the *** this work,poly(butyleneadipate-co-terephthalate)(PBAT)is employed as a model biodegradable plastic to study the specific ion effects on the enzymatic degradation of polyester *** results show that the specific ion effects on the enzymatic degradation rate of the PBAT films and on the catalytic rate constant for the enzymatic hydrolysis of the ester bonds are strongly dependent on temperature and ionic *** the enzymatic degradation rate and catalytic rate constant decrease following the trends Na^(+)>K^(+)>Ca^(2+)and Cl^(-)>SO_(4)^(2-)>NO_(3)^(-)for cations and anions,respectively,indicating that the ion-specific enzymatic degradation of the PBAT films is closely correlated with the specific ion effects on enzymatic hydrolysis of the ester *** study shows that the specific ion effects on the enzyme activity can be understood by taking into account the ion-specific cation-anion interaction,ionic dispersion force,salting-out effect and salting-in *** study of specific ion effects on the enzymatic hydrolysis of the ester bonds and the resultant enzymatic degradation of the PBAT films would offer us a new clue to develop new biodegradable,environmentally friendly synthetic plastics.

关键词： Specific ion effects Biodegradable films Ion-enzyme interactions Enzyme activity

来源：评论

学校读者我要写书评

暂无评论

CBNet: Cooperation-Based Weakly Supervised Polyp Detection 24

CBNet: Cooperation-Based Weakly Supervised Polyp Detection

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Du, Xiuquan Chen, Jiajia Zhang, Xuejun Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Anhui Hefei China School of Computer Science and Technology Anhui University Anhui Hefei China

ISBN: (纸本)9798400706868

Missed polyps are the major risk factor for colorectal cancer. To minimize misdiagnosis, many methods have been developed. However, they either rely on laborious instance-level annotations, require labeling of prompt points, or lack the ability to filter noise proposals and detect polyps integrally, resulting in severe challenges in this area. In this paper, we propose a novel Cooperation-Based network (CBNet), a two-stage polyp detection framework supervised by image labels that removes wrong proposals through classification in collaboration with segmentation and obtains a more accurate detector by aggregating adaptive multi-level regional features. Specifically, we conduct a Cooperation-Based Region Proposal Network (CBRPN) to reduce the negative impact of noises by deleting proposals without polyps, enabling our network to capture polyp features. Moreover, to enhance location integrity and classification precision of polyps, we aggregate multi-level region of interest (ROI) features under the guidance of the backbone classification layer, namely Adaptive ROI Fusion Module (ARFM). Extensive experiments on the public and private datasets show that our method achieves state-of-the-art performance for weakly supervised methods and even outperforms full supervision in some terms. All code is available at https://***/dxqllp/CBNet. © 2024 ACM.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning 38

Leveraging Catastrophic Forgetting to Develop Safe Diffusion...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Pan, Jiadong Gao, Hongcheng Wu, Zongyu Hu, Taihang Su, Li Huang, Qingming Li, Liang Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS China University of Chinese Academy of Sciences China The Pennsylvania State University United States Nankai University China

Diffusion models (DMs) have demonstrated remarkable proficiency in producing images based on textual prompts. Numerous methods have been proposed to ensure these models generate safe images. Early methods attempt to incorporate safety filters into models to mitigate the risk of generating harmful images but such external filters do not inherently detoxify the model and can be easily bypassed. Hence, model unlearning and data cleaning are the most essential methods for maintaining the safety of models, given their impact on model parameters. However, malicious fine-tuning can still make models prone to generating harmful or undesirable images even with these methods. Inspired by the phenomenon of catastrophic forgetting, we propose a training policy using contrastive learning to increase the latent space distance between clean and harmful data distribution, thereby protecting models from being fine-tuned to generate harmful images due to forgetting. The experimental results demonstrate that our methods not only maintain clean image generation capabilities before malicious fine-tuning but also effectively prevent DMs from producing harmful images after malicious fine-tuning. Our method can also be combined with other safety methods to maintain their safety against malicious fine-tuning further. WARNING: This paper contains offensive images generated by models. © 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

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：