检索结果-内蒙古大学图书馆

Spiking Reinforcement Learning Enhanced by Bioinspired Event Source of Multi-dendrite Spiking Neuron and Dynamic Thresholds

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 618-629页

作者： Xingyue Liang Qiaoyun Wu Yun Zhou Chunyu Tan Hongfu Yin Changyin Sun the School of Artificial Intelligence Anhui University Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education IEEE the Institute of Artificial Intelligence Hefei Comprehensive National Science Center the School of Automation Southeast University the Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education

Deep reinforcement learning(DRL) achieves success through the representational capabilities of deep neural networks(DNNs). Compared to DNNs, spiking neural networks(SNNs),known for their binary spike information processing, exhibit more biological characteristics. However, the challenge of using SNNs to simulate more biologically characteristic neuronal dynamics to optimize decision-making tasks remains, directly related to the information integration and transmission in *** by the advanced computational power of dendrites in biological neurons, we propose a multi-dendrite spiking neuron(MDSN) model based on Multi-compartment spiking neurons(MCN), expanding dendrite types from two to multiple and deriving the analytical solution of somatic membrane *** apply the MDSN to deep distributional reinforcement learning to enhance its performance in executing complex decisionmaking tasks. The proposed model can effectively and adaptively integrate and transmit meaningful information from different sources. Our model uses a bioinspired event-enhanced dendrite structure to emphasize features. Meanwhile, by utilizing dynamic membrane potential thresholds, it adaptively maintains the homeostasis of MDSN. Extensive experiments on Atari games show that the proposed model outperforms some state-of-the-art spiking distributional RL models by a significant margin.

关键词： Deep reinforcement learning multi-compartment spiking neurons spiking neural network

来源：评论

学校读者我要写书评

暂无评论

Power Switching Based on Trajectory Planning and Sliding Mode Control for Solid Oxide Fuel Cell Systems

引用

Journal of Modern Power Systems and Clean Energy 2024年第6期12卷 1968-1979页

作者： Zhen Wang Guoqiang Liu Xingbo Liu Jie Wang Zhiyang Jin Xiaowei Fu Zhuo Wang Bing Jin Zhonghua Deng Xi Li Key Laboratory of Imaging Processing and Intelligent Control of Ministry of Education School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhanChina Research Institute of Huazhong University of Science and Technology in Shenzhen ShenzhenChina Hubei Huazhong Electric Power Technology Development Co. Ltd.WuhanChina School of Computer Science and Technology Wuhan University of Science and TechnologyWuhanChina School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhanChinaand he is also with the Wuhan Huamao Automation Co.Ltd.WuhanChina

To improve the safety of the solid oxide fuel cell(SOFC)systems and avoid the generation of large amounts of pollutants during power switching,this paper designs a power switching strategy based on trajectory planning and sliding mode control(TP-SMC).The design elements of the power switching strategy are proposed through simulation analysis at ***,based on the gas transmission delay time and the change of gas flow obtained from testing,trajectory planning(TP)is *** with other power switching strategies,it has been proven that the power switching strategy based on TP has significantly better control ***-thermore,considering the shortcomings and problems of TP in practical application,this paper introduces sliding mode control(SMC)on the basis of TP to improve the power switching *** final simulation results also prove that the TP-SMC can effectively suppress the impact of uncertainty in gas flow and gas transmission delay *** with TP,TP-SMC can ensure that under uncertain conditions,the SOFC system does not experience fuel starvation and temperature exceeding limit during power ***,the NOx emissions are also within the normal and acceptable *** paper can guide the power switching process of the actual SOFC sys-tems to avoid safety issues and excessive generation of NOx,which is very helpful for improving the performance and ser-vice lifeof the SOFCsystems.

关键词： Solid oxide fuel cell(SOFC)system power switching safety NOx emission trajectory planning sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Scene text recognition via dual character counting-aware visual and semantic modeling network

引用

science China(Information sciences) 2024年第3期67卷 313-314页

作者： Ke XIAO Anna ZHU Brian Kenji IWANA Cheng-Lin LIU School of Computer Science and Artificial Intelligence Wuhan University of Technology Human Interface Laboratory Kyushu University State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences

Scene text recognition(STR) is drawing increasing attention nowadays due to its wide application in real life. Character counting information, as auxiliary information, has been shown to be effective in boosting text ... 详细信息

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

An optimized ensemble model based on meta-heuristic algorithms for effective detection and classification of breast tumors

引用

Neural Computing and Applications 2025年第6期37卷 4881-4894页

作者： Saber, Abeer Elbedwehy, Samar Awad, Wael A. Hassan, Esraa Information Technology Department Faculty of Computers and Artificial Intelligence Damietta University Damietta34517 Egypt Department of Data Science Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33511 Egypt Department of Computer Science Faculty of Computers and Artificial Intelligence Damietta University Damietta34517 Egypt Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33511 Egypt

One of the most common cancers among women worldwide is breast cancer (BC), and early diagnosis can save lives. Early detection of BC increases the likelihood of a successful outcome by enabling treatment to start sooner. Even in areas without access to a specialist physician, machine learning (ML) aids in early BC detection. The medical imaging community is becoming more interested in using ML, and deep learning (DL) to increase the accuracy of cancer screening. Many disease-related data are sparse. However, for DL models to perform well, a large amount of data is required. Because of this, the DL models that are currently in use on medical images are not as effective as they could be. Convolutional neural network (CNN) models have recently gained popularity in the medical industry, and they perform admirably in terms of high performance and robustness at image classification. The proposed method classifies data using ensemble pre-trained models such as the dense convolutional network (DenseNet)-121 and EfficientNet-B5 feature extractor networks, as well as the support vector machine for classification. Using a modified meta-heuristic optimizer, the selected pre-trained CNN hyperparameters were optimized to improve the performance. The experimental results for the presented model on the INbreast dataset show that the EfficientNet-B5 model is effective for BC classification, with overall accuracy, sensitivity, specificity, precision, and area under the ROC curve (AUC) values of 99.9%, 99.9%, 99.8%, 99.1%, 1.0, respectively. © The Author(s) 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

引用

Chinese Physics B 2023年第9期32卷 596-602页

作者：陈单蔡德福苏厚胜 School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074China Institute of Artificial Intelligence Huazhong University of Science and TechnologyWuhan 430074China State Grid Hubei Electric Power Research Institute Wuhan 430077China

Real-world networks exhibit complex topological interactions that pose a significant computational challenge to analyses of such *** to limited resources,there is an urgent need to develop dimensionality reduction techniques that can significantly reduce the structural complexity of initial large-scale *** this paper,we propose a subgraph extraction method based on the node centrality measure to reduce the size of the initial network ***,nodes with smaller centrality value are removed from the initial network to obtain a subgraph with a smaller *** results demonstrate that various real-world networks,including power grids,technology,transportation,biology,social,and language networks,exhibit self-similarity behavior during the reduction *** present results reveal the selfsimilarity and scale invariance of real-world networks from a different perspective and also provide an effective guide for simplifying the topology of large-scale networks.

关键词： complex networks subgraph extraction self-similarity scale invariance

来源：评论

学校读者我要写书评

暂无评论

Cross-Lingual Sentence Compression for Length-Constrained Subtitles in Low-Resource Settings 31

Cross-Lingual Sentence Compression for Length-Constrained Su...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Jørgensen, Tollef Emil Mengshoel, Ole Jakob Norwegian University of Science and Technology Data and Artificial Intelligence Group Norway

ISBN: (纸本)9798891761964

This paper explores the joint task of machine translation and sentence compression, emphasizing its application in subtitle generation for broadcast and live media for low-resource languages and hardware. We develop CLSC (Cross-Lingual Sentence Compression), a system trained on openly available parallel corpora organized by compression ratios, where the target length is constrained to a fraction of the source sentence length. We present two training methods: 1) Multiple Models (MM), where individual models are trained separately for each compression ratio, and 2) a Controllable Model (CM), a single model per language using a compression token to encode length constraints. We evaluate both subtitle data and transcriptions from the EuroParl corpus. To accommodate low-resource settings, we constrain data sampling for training and show results for transcriptions in French, Hungarian, Lithuanian, and Polish and subtitles in Albanian, Basque, Malay, and Norwegian. Our models preserve high semantic meaning and metric evaluations for compressed contexts. © 2025 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

OCRBench: on the hidden mystery of OCR in large multimodal models

引用

science China(Information sciences) 2024年第12期67卷 23-35页

作者： Yuliang LIU Zhang LI Mingxin HUANG Biao YANG Wenwen YU Chunyuan LI Xu-Cheng YIN Cheng-Lin LIU Lianwen JIN Xiang BAI School of Artificial Intelligence and Automation Huazhong University of Science and Technology School of Electronic and Information Engineering South China University of Technology Microsoft Research School of Computer & Communication Engineering University of Science and Technology Beijing Institute of Automation Chinese Academy of Sciences School of Software Engineering Huazhong University of Science and Technology

Large models have recently played a dominant role in natural language processing and multimodal vision-language learning. However, their effectiveness in text-related visual tasks remains relatively unexplored. In this paper, we conducted a comprehensive evaluation of large multimodal models, such as GPT4V and Gemini, in various text-related visual tasks including text recognition, scene text-centric visual question answering(VQA), document-oriented VQA, key information extraction(KIE), and handwritten mathematical expression recognition(HMER). To facilitate the assessment of optical character recognition(OCR) capabilities in large multimodal models, we propose OCRBench, a comprehensive evaluation benchmark. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available. Furthermore, our study reveals both the strengths and weaknesses of these models, particularly in handling multilingual text, handwritten text, non-semantic text, and mathematical expression *** importantly, the baseline results presented in this study could provide a foundational framework for the conception and assessment of innovative strategies targeted at enhancing zero-shot multimodal *** evaluation pipeline and benchmark are available at https://***/Yuliang-Liu/Multimodal OCR.

关键词： large multimodal model OCR text recognition scene text-centric VQA document-oriented VQA key information extraction handwritten mathematical expression recognition

来源：评论

学校读者我要写书评

暂无评论

Dynamic SLAM Visual Odometry Based on Instance Segmentation:A Comprehensive Review

引用

Computers, Materials & Continua 2024年第1期78卷 167-196页

作者： Jiansheng Peng Qing Yang Dunhua Chen Chengjun Yang Yong Xu Yong Qin College of Automation Guangxi University of Science and TechnologyLiuzhou545000China Department of Artificial Intelligence and Manufacturing Hechi UniversityHechi547000China

Dynamic Simultaneous Localization and Mapping(SLAM)in visual scenes is currently a major research area in fields such as robot navigation and autonomous ***,in the face of complex real-world envi-ronments,current dynamic SLAM systems struggle to achieve precise localization and map *** the advancement of deep learning,there has been increasing interest in the development of deep learning-based dynamic SLAM visual odometry in recent years,and more researchers are turning to deep learning techniques to address the challenges of dynamic *** to dynamic SLAM systems based on deep learning methods such as object detection and semantic segmentation,dynamic SLAM systems based on instance segmentation can not only detect dynamic objects in the scene but also distinguish different instances of the same type of object,thereby reducing the impact of dynamic objects on the SLAM system’s *** article not only introduces traditional dynamic SLAM systems based on mathematical models but also provides a comprehensive analysis of existing instance segmentation algorithms and dynamic SLAM systems based on instance segmentation,comparing and summarizing their advantages and *** comparisons on datasets,it is found that instance segmentation-based methods have significant advantages in accuracy and robustness in dynamic ***,the real-time performance of instance segmentation algorithms hinders the widespread application of dynamic SLAM *** recent years,the rapid development of single-stage instance segmentationmethods has brought hope for the widespread application of dynamic SLAM systems based on instance ***,possible future research directions and improvementmeasures are discussed for reference by relevant professionals.

关键词： Dynamic SLAM instance segmentation visual odometry

来源：评论

学校读者我要写书评

暂无评论

Element relational graph-augmented multi-granularity contextualized encoding for document-level event role filler extraction

引用

Frontiers of Computer science 2025年第2期19卷 137-138页

作者： Enchang ZHU Zhengtao YU Yuxin HUANG Shengxiang GAO Yantuan XIAN Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and TechnologyKunming 650500China

1 Introduction Document-level Role Filler Extraction aims to identify those spans of text that denote the role fillers for each event described in the document[1].Despite achieving certain accomplishments,existing methods are still not effective due to the following two issues:(1)there are difficulties in contextual modeling of long text,which requires modeling and understanding coherence and connections across sentences and paragraphs;(2)there usually ignore the explicit dependency relationships between event elements displayed in long *** this end,we propose a novel graph-augmented approach for document-level event role filler extraction,named element relational graph-augmented multi-granularity contextualized encoder(ERGM),whose main idea is to effectively enhance the model's capabilities in capturing deep semantic information of events in long texts and modeling dependency relationships among event elements by incorporating the Event elements relational ***,this method first constructs the structural graph by extracting elements from the source document.

关键词： contextual spite semantic

来源：评论

学校读者我要写书评

暂无评论

Semantic segmentation via pixel-to-center similarity calculation

引用

CAAI Transactions on intelligence technology 2024年第1期9卷 87-100页

作者： Dongyue Wu Zilin Guo Aoyan Li Changqian Yu Nong Sang Changxin Gao National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhanChina Meituan Inc. BeijingChina

Since the fully convolutional network has achieved great success in semantic segmentation,lots of works have been proposed to extract discriminative pixel ***,the authors observe that existing methods still suffer from two typical challenges:(i)The intra-class feature variation between different scenes may be large,leading to the difficulty in maintaining the consistency between same-class pixels from different scenes;(ii)The inter-class feature distinction in the same scene could be small,resulting in the limited performance to distinguish different classes in each *** authors first rethink se-mantic segmentation from a perspective of similarity between pixels and class *** weight vector of the segmentation head represents its corresponding semantic class in the whole dataset,which can be regarded as the embedding of the class ***,the pixel-wise classification amounts to computing similarity in the final feature space between pixels and the class *** this novel view,the authors propose a Class Center Similarity(CCS)layer to address the above-mentioned challenges by generating adaptive class centers conditioned on each scenes and supervising the similarities between class *** CCS layer utilises the Adaptive Class Center Module to generate class centers conditioned on each scene,which adapt the large intra-class variation between different *** designed Class Distance Loss(CD Loss)is introduced to control both inter-class and intra-class distances based on the predicted center-to-center and pixel-to-center ***,the CCS layer outputs the processed pixel-to-center similarity as the segmentation *** experiments demonstrate that our model performs favourably against the state-of-the-art methods.

关键词： computer vision deep neural networks image segmentation scene understanding

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：