检索结果-内蒙古大学图书馆

Mindstorms in natural language-based societies of mind

Computational Visual Media 2025年第1期11卷 29-81页

作者： Mingchen Zhuge Haozhe Liu Francesco Faccio Dylan R.Ashley Róbert Csordás Anand Gopalakrishnan Abdullah Hamdi Hasan Abed Al Kader Hammoud Vincent Herrmann Kazuki Irie Louis Kirsch Bing Li Guohao Li Shuming Liu Jinjie Mai Piotr Piękos Aditya A.Ramesh Imanol Schlag Weimin Shi Aleksandar Stanić Wenyi Wang Yuhui Wang Mengmeng Xu Deng-Ping Fan Bernard Ghanem and Jürgen Schmidhuber Center of Excellence for Generative AI King Abdullah University of Science and TechnologyThuwalSaudi Arabia Dalle Molle Institute for Artificial Intelligence Research LuganoSwitzerland Stanford University CaliforniaUSA Oxford University OxfordUK Harvard University CambridgeUSA ETH AI Center ZurichSwitzerland Beihang University BeijingChina CS&VCIP Nankai UniversityTianjinChina

Inspired by Minsky’s Society of Mind,Schmidhuber’s Learning to Think,and other more 9-16 recent works,this paper proposes and advocates for the concept of natural language-based societies of mind(NLSOMs).We imagine these societies as consisting of a collection of multimodal neural networks,including large language models,which engage in a“mindstorm”to solve problems using a shared natural language ***,we work to identify and discuss key questions about the social structure,governance,and economic principles for NLSOMs,emphasizing their impact on the future of *** demonstrations with NLSOMs—which feature up to 129 agents—show their effectiveness in various tasks,including visual question answering,image captioning,and prompt generation for text-to-image synthesis.

关键词： mindstorm society of mind(SOM) large languagemodels(LLMs) multimodal learning learning to think

来源：评论

学校读者我要写书评

暂无评论

Generative Image Steganography Based on Latent Space Vector Coding and Diffusion Model 1

引用

2nd International Conference on artificial intelligence Security and Privacy, AIS and P 2024

作者： Liu, Weisong Yang, Jianfeng Huang, Jiewen El-Latif, Ahmed A. Abd Zhou, Zhili School of Artificial Intelligence Guangzhou University Guangzhou China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China EIAS Data Science Lab College of Computer and Information Sciences and Center of Excellence in Quantum and Intelligent Computing Prince Sultan University Riyadh11586 Saudi Arabia

ISBN: (数字)9789819611485

ISBN: (纸本)9789819611478

Image steganography is a technology that embed secret information within a cover image to obtain a stego-image for covert communication. The transmission of undetectable stego-images via social media can facilitate secure and efficient covert communication. Recently, the generative image steganography has achieved promising performance with the rapid development of generative models. However, existing generative image steganography suffers from issues, i.e., the low quality of the generated stego-image and the limited hiding capacity. To address these issues, this paper proposes a generative image steganography scheme based on latent space vector coding and diffusion model. It consists of an optimized diffusion denoising network, the latent space vector coding mapping network, and the information extraction network. In this scheme, the secret information is encoded as a latent space vector, which is then transformed in the input diffusion model to generate the stego-image. Experimental results demonstrate that this scheme achieves superior performance compared with existing generative image steganography methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Advancements in Liver Tumor Detection:A Comprehensive Review of Various Deep Learning Models

引用

Computer Modeling in Engineering & sciences 2025年第1期142卷 91-122页

作者： Shanmugasundaram Hariharan D.Anandan Murugaperumal Krishnamoorthy Vinay Kukreja Nitin Goyal Shih-Yu Chen Deptartment of Artificial Intelligence and Data Science Vardhaman College of EngineeringHyderabad501218India Deptartment of CSE V.S.B College of EngineeringKarur639111India Deptartment of Electrical and Electronics Engineering Vardhaman College of EngineeringHyderabad501218India Centre for Research Impact&Outcome Chitkara UniversityRajpura140401PunjabIndia Department of Computer Science and Engineering School of Engineering and TechnologyCentral University of HaryanaMahendergarh123031HaryanaIndia Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin64002Taiwan Intelligence Recognition Industry Service Research Center National Yunlin University of Science and TechnologyYunlin64002Taiwan

Liver cancer remains a leading cause of mortality worldwide,and precise diagnostic tools are essential for effective treatment *** Tumors(LTs)vary significantly in size,shape,and location,and can present with tissues of similar intensities,making automatically segmenting and classifying LTs from abdominal tomography images crucial and *** review examines recent advancements in Liver Segmentation(LS)and Tumor Segmentation(TS)algorithms,highlighting their strengths and limitations regarding precision,automation,and *** metrics are utilized to assess key detection algorithms and analytical methods,emphasizing their effectiveness and relevance in clinical *** review also addresses ongoing challenges in liver tumor segmentation and identification,such as managing high variability in patient data and ensuring robustness across different imaging *** suggests directions for future research,with insights into technological advancements that can enhance surgical planning and diagnostic accuracy by comparing popular *** paper contributes to a comprehensive understanding of current liver tumor detection techniques,provides a roadmap for future innovations,and improves diagnostic and therapeutic outcomes for liver cancer by integrating recent progress with remaining challenges.

关键词： Liver tumor detection liver tumor segmentation image processing liver tumor diagnosis feature extraction tumor classification deep learning machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Feature Fusion and Advanced Representation Learning for Multi Label Image Classification

引用

Computers, Materials & Continua 2025年第3期82卷 5285-5306页

作者： Naikang Zhong Xiao Lin Wen Du Jin Shi Institute of Artificial Intelligence on Education Research College of InformationMechanical and Electrical EngineeringShanghai Normal UniversityShanghai200234China Lab for Educational Big Data and Policymaking Ministry of EducationShanghai Normal UniversityShanghai200234China Shanghai Intelligent Education Big Data Engineering Technology Research Center Shanghai Normal UniversityShanghai200234China Shanghai Online Education Research Base for Primary and Secondary Schools Shanghai200234China DS Information Technology Co. Ltd.Shanghai200032China Faculty of Innovation Engineering Macao university of Science and TechnologyMacao999078China

Multi-label image classification is a challenging task due to the diverse sizes and complex backgrounds of objects in *** class-specific precise representations at different scales is a key aspect of feature ***,existing methods often rely on the single-scale deep feature,neglecting shallow and deeper layer features,which poses challenges when predicting objects of varying scales within the same *** some studies have explored multi-scale features,they rarely address the flow of information between scales or efficiently obtain class-specific precise representations for features at different *** address these issues,we propose a two-stage,three-branch Transformer-based *** first stage incorporates multi-scale image feature extraction and hierarchical scale *** design enables the model to consider objects at various scales while enhancing the flow of information across different feature scales,improving the model’s generalization to diverse object *** second stage includes a global feature enhancement module and a region selection *** global feature enhancement module strengthens interconnections between different image regions,mitigating the issue of incomplete represen-tations,while the region selection module models the cross-modal relationships between image features and ***,these components enable the efficient acquisition of class-specific precise feature *** experiments on public datasets,including COCO2014,VOC2007,and VOC2012,demonstrate the effectiveness of our proposed *** approach achieves consistent performance gains of 0.3%,0.4%,and 0.2%over state-of-the-art methods on the three datasets,*** results validate the reliability and superiority of our approach for multi-label image classification.

关键词： Image classification multi-label multi scale attention mechanisms feature fusion

来源：评论

学校读者我要写书评

暂无评论

Puzzle mode graph learning with pattern composition relationships reasoning for defect detection of printed products

引用

Journal of Manufacturing Systems 2025年 81卷 34-48页

作者： Zixun Zhu Jie Zhang Junliang Wang Peng Zhang Jiacheng Li College of Mechanical Engineering Donghua University Shanghai China Engineering Research Center of Artificial Intelligence for Textile Industry Ministry of Education Institute of Artificial Intelligence Donghua University Shanghai China Shanghai Engineering Research Center of Industrial Big Data Intelligent System Institute of Artificial Intelligence Donghua University Shanghai China College of Materials Science and Engineering Donghua University Shanghai China

Patterns are designs composed of specific elements and are widely present in various printed products, representing particular design intentions. However, due to printing errors, pattern defects are extremely common in these products, significantly impacting their visual quality and market price, especially in high-value customized products like luxury apparel, premium wallpapers and decorative tiles. Traditional detection methods struggle to provide effective judgments with conventional visual cues purely and frequently fall short due to the intricate nature of the pattern composition. To overcome this challenge, we propose a puzzle mode graph learning method capable of reasoning about pattern composition relationships. This novel detection framework simulates the logical reasoning ability of humans in assembling unordered puzzle pieces into a complete pattern, thus surpassing spatial structure limitations and enabling structural defect detection in patterns. Specifically, a parametric representation function is integrated into convolutional layers to enhance the segmentation accuracy of shape masks. Then, cross-graph semantic matching rules are developed to dynamically re-encode the adjacency matrix, enabling the construction of an attribute relationship graph that explicitly describes pattern attributes, including pattern elements, color sequences and shape positions. Moreover, the defective reasoning mechanism calculates puzzle-mode scores to decouple semantic relationships of defect features, inferring anomalous node and edge weights affecting the graph structure, thereby facilitating more precise judgments of pattern defects. Comparative experiments conducted on a real printed defect dataset validate this method. Results demonstrate its effectiveness and robustness in identifying complex pattern defects, providing essential support for appearance quality control in high-end industrial products.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The interaction between KIF21A and KANK1 regulates dendritic morphology and synapse plasticity in neurons

引用

Neural Regeneration research 2025年第1期20卷 209-223页

作者： Shi-Yan Sun Lingyun Nie Jing Zhang Xue Fang Hongmei Luo Chuanhai Fu Zhiyi Wei Ai-Hui Tang Hefei National Research Center for Physical Sciences at the Microscale CAS Key Laboratory of Brain Function and DiseaseMinistry of Education Key Laboratory for Membrane-less Organelles and Cellular DynamicsDivision of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefeiAnhui ProvinceChina Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefeiAnhui ProvinceChina CAS Center for Excellence in Molecular Cell Sciences Division of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefeiAnhui ProvinceChina Department of Neurobiology School of Life SciencesSouthern University of Science and TechnologyShenzhenGuangdong ProvinceChina Brain Research Center Southern University of Science and TechnologyShenzhenGuangdong ProvinceChina

Morphological alterations in dendritic spines have been linked to changes in functional communication between neurons that affect learning and ***-4 KIF21A helps organize the microtubule-actin network at the cell cortex by interacting with KANK1;however,whether KIF21A modulates dendritic structure and function in neurons remains *** this study,we found that KIF21A was distributed in a subset of dendritic spines,and that these KIF21A-positive spines were larger and more structurally plastic than KIF21A-negative ***,the interaction between KIF21A and KANK1 was found to be critical for dendritic spine morphogenesis and synaptic *** of either KIF21A or KANK1 inhibited dendritic spine morphogenesis and dendritic branching,and these deficits were fully rescued by coexpressing full-length KIF21A or KANK1,but not by proteins with mutations disrupting direct binding between KIF21A and KANK1 or binding between KANK1 and *** down KIF21A in the hippocampus of rats inhibited the amplitudes of long-term potentiation induced by high-frequency stimulation and negatively impacted the animals’cognitive *** together,our findings demonstrate the function of KIF21A in modulating spine morphology and provide insight into its role in synaptic function.

关键词： actin cytoskeleton dendrite KANK1 KIF21A microtubule spine morphology spine synaptic plasticity talin1

来源：评论

学校读者我要写书评

暂无评论

Real-Time Proportional-Integral-Derivative(PID)Tuning Based on Back Propagation(BP)Neural Network for Intelligent Vehicle Motion Control

引用

Computers, Materials & Continua 2025年第5期83卷 2375-2401页

作者： Liang Zhou Qiyao Hu Xianlin Peng Qianlong Liu School of Information Science and Technology Northwest UniversityXi’an710127China State-Province Joint Engineering and Research Center of Advanced Networking and Intelligent Information Services Northwest UniversityXi’an710127China Generative Artificial Intelligence and Mixed Reality Key Laboratory of Higher Education Institutions in Shaanxi Province Xi’an710127China Shaanxi Silk Road Cultural Heritage Digital Protection and Inheritance Collaborative Innovation Center Xi’an710127China School of Art Northwest UniversityXi’an710127China Network and Data Center Northwest UniversityXi’an710127China

Over 1.3 million people die annually in traffic accidents,and this tragic fact highlights the urgent need to enhance the intelligence of traffic safety and control *** modern industrial and technological applications and collaborative edge intelligence,control systems are crucial for ensuring efficiency and ***,deficiencies in these systems can lead to significant operational *** paper uses edge intelligence to address the challenges of achieving target speeds and improving efficiency in vehicle control,particularly the limitations of traditional Proportional-Integral-Derivative(PID)controllers inmanaging nonlinear and time-varying dynamics,such as varying road conditions and vehicle behavior,which often result in substantial discrepancies between desired and actual speeds,as well as inefficiencies due to manual parameter *** paper uses edge intelligence to propose a novel PID control algorithm that integrates Backpropagation(BP)neural networks to enhance robustness and *** BP neural network is first trained to capture the nonlinear dynamic characteristics of the *** network is then combined with the PID controller to forma hybrid control *** output layer of the neural network directly adjusts the PIDparameters(k_(p),k_(i),k_(d)),optimizing performance for specific driving scenarios through self-learning and weight *** experiments demonstrate that our BP neural network-based PID design significantly outperforms traditional methods,with the response time for acceleration from 0 to 1 m/s improved from 0.25 s to just 0.065 ***,real-world tests on an intelligent vehicle show its ability to make timely adjustments in response to complex road conditions,ensuring consistent speed maintenance and enhancing overall system performance.

关键词： PID control backpropagation neural network hybrid control nonlinear dynamic processes edge intelligence

来源：评论

学校读者我要写书评

暂无评论

MVLA-Net:A Multi-View Lesion Attention Network for Advanced Diagnosis and Grading of Diabetic Retinopathy

引用

Computers, Materials & Continua 2025年第4期83卷 1173-1193页

作者： Tariq Mahmood Tanzila Saba Faten S.Alamri Alishba Tahir Noor Ayesha Artificial Intelligence and Data Analytics(AIDA)Lab College of Computer&Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Faculty of Information Sciences University of EducationVehari CampusVehari61100Pakistan Department of Mathematical Sciences College of SciencePrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia Shifa College of Medicine Shifa Tameer-E-Millat UniversityIslamabad44000Pakistan Center of Excellence in Cyber Security(CYBEX) Prince Sultan UniversityRiyadh11586Saudi Arabia

Innovation in learning algorithms has made retinal vessel segmentation and automatic grading tech-niques crucial for clinical diagnosis and prevention of diabetic *** traditional methods struggle with accuracy and reliability due to multi-scale variations in retinal blood vessels and the complex pathological relationship in fundus images associated with diabetic *** the single-modal diabetic retinopathy grading network addresses class imbalance challenges and lesion representation in fundus image data,dual-modal diabetic retinopathy grading methods offer superior ***,the scarcity of dual-modal data and the lack of effective feature fusion methods limit their potential due to multi-scale *** paper addresses these issues by focusing on multi-scale retinal vessel segmentation,dual feature fusion,data augmentation,and attention-based *** proposed model aims to improve comprehensive segmentation for retinal images with varying vessel *** employs a dual-branch parallel architecture that integrates a transformer encoder with a convolutional neural network encoder to extract local and global information for synergistic saliency *** that,the model uses residual structures and attention modules to extract critical lesions,enhancing the accuracy and reliability of diabetic retinopathy *** evaluate the efficacy of the proposed approach,this study compared it with other pre-trained publicly open models,ResNet152V2,ConvNext,Efficient Net,DenseNet,and Swin Transform,with the same developmental *** models achieved approximately 85%accuracy with the same image preparation ***,the proposed approach outperforms and optimizes existing models by achieving an accuracy of 99.17%,99.04%,and 99.24%,on Kaggle APTOS19,IDRiD,and EyePACS datasets,*** results support the model’s utility in helping ophthalmologists diagnose diabetic retinopathy more rapidly and accurat

关键词： Diabetic retinopathy grading retinal vessel segmentation dual-modal deep learning attention mecha-nism health risks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline data

arXiv

引用

arXiv 2025年

作者： Deng, Shilong Zheng, Zetao He, Hongcai Weng, Paul Shao, Jie University of Electronic Science and Technology of China Chengdu China Sichuan Artificial Intelligence Research Institute Yibin China Data Science Research Center Duke Kunshan University Kunshan China

A major challenge in Reinforcement Learning (RL) is the difficulty of learning an optimal policy from sparse rewards. Prior works enhance online RL with conventional Imitation Learning (IL) via a handcrafted auxiliary objective, at the cost of restricting the RL policy to be sub-optimal when the offline data is generated by a non-expert policy. Instead, to better leverage valuable information in offline data, we develop Generalized Imitation Learning from Demonstration (GILD), which meta-learns an objective that distills knowledge from offline data and instills intrinsic motivation towards the optimal policy. Distinct from prior works that are exclusive to a specific RL algorithm, GILD is a flexible module intended for diverse vanilla off-policy RL algorithms. In addition, GILD introduces no domain-specific hyperparameter and minimal increase in computational cost. In four challenging MuJoCo tasks with sparse rewards, we show that three RL algorithms enhanced with GILD significantly outperform state-of-the-art methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Network Architecture Search Method for Solving Partial Differential Equations

arXiv

引用

arXiv 2025年

作者： Li, Qing Chen, Jingrun School of Artificial Intelligence and Data Science University of Science and Technology of China China School of Mathematical Sciences Suzhou Institute for Advanced Research University of Science and Technology of China China Suzhou Big Data & AI Research and Engineering Center China

Solving partial differential equations (PDEs) has been indispensable in scientific and engineering applications. Recently, deep learning methods have been widely used to solve high-dimensional problems. The interplay between deep learning and numerical PDEs has resulted in a variety of new methods, one of which is the physics-informed neural network (PINN). Typically, a deep learning method has three main components: a neural network, a loss function, and an optimizer. While the construction of the loss function is rooted in the definition of solution space, how to choose a optimal neural network is somewhat ad hoc, leaving much room for improvement. In the framework of PINN, we propose an unsupervised network architecture search method for solving PDEs, termed PINN-DARTS, which applies the differentiable architecture search (DARTS) to find the optimal network architecture structure in a given set of neural networks. In this set, the number of layers and the number of neurons in each layer can change. In the searching phase, both network and architecture parameters are updated simultaneously, so the running time is close to that of PINN with a pre-determined network structure. Unlike available works, our approach is unsupervised and purely based on the PDE residual without any prior usage of solutions. PINN-DARTS outputs the optimal network structure as well as the associated numerical solution. The performance of PINN-DARTS is verified on several benchmark PDEs, including elliptic, parabolic, wave, and Burgers’ equations. Compared to traditional architecture search methods, PINN-DARTS achieves significantly higher architectural accuracy. Another interesting observation is that both the solution complexity and the PDE type have a prominent impact on the optimal network architecture. Our study suggests that architectures with uneven widths from layer to layer may have superior performance across different solution complexities and different PDE types. Copyright © 202

关键词： Wave equations

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：