检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhao, Qingsong Wang, Yi Dou, Shuguang Gong, Chen Wang, Yin Zhao, Cairong Ji, Xiaopeng Jiang, Xinyang Department of Computer Science and Technology Tongji University Shanghai201804 China Shanghai AI Laboratory Shanghai200232 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information School of Computer Science and Engineering Ministry of Education Nanjing University of Science and Technology Nanjing210094 China The State Key Lab of CAD&CG Zhejiang University China Shanghai China

How to improve discriminative feature learning is central in classification. Existing works address this problem by explicitly increasing inter-class separability and intra-class compactness, whether by constructing positive and negative pairs for contrastive learning or posing tighter class separating margins. These methods do not exploit the similarity between different classes as they adhere to independent identical distributions assumption in data. In this paper, we embrace the real-world data distribution setting that some classes share semantic overlaps due to their similar appearances or concepts. Regarding this hypothesis, we propose a novel regularization to improve discriminative learning. We first calibrate the estimated highest likelihood of one sample based on its semantically neighboring classes, then encourage the overall likelihood predictions to be deterministic by imposing an adaptive exponential penalty. As the gradient of the proposed method is roughly proportional to the uncertainty of the predicted likelihoods, we name it adaptive discriminative regularization (ADR), trained along with a standard cross entropy loss in classification. Extensive experiments demonstrate that it can yield consistent and non-trivial performance improvements in a variety of visual classification tasks (over 10 benchmarks). Furthermore, we find it is robust to long-tailed and noisy label data distribution. Its flexible design enables its compatibility with mainstream classification architectures and losses. © 2022, CC BY.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Research on machining accuracy of workpiece oriented to autonomous behavior of equipment 26

Research on machining accuracy of workpiece oriented to auto...

引用

26th International Conference on Automation and Computing, ICAC 2021

作者： Ma, Honglong Liu, Yefeng Sun, Weitang Liu, Yiming Zhang, Qichun Shenyang Institute of Technology Liaoning Key Lab. of Information Physics Fusion and Intelligent Manufacturing for Grade CNC Machine Fushun113122 China Shenyang Institute of Technology College of Mechanical and Vehicle Engineering Fushun113122 China University of Bradford Department of Computer Science BradfordBD7 1DP United Kingdom

ISBN: (纸本)9781860435577

Around the problem of workpiece machining accuracy, a model of autonomous behavior of equipment and the method of establishing patterns in knowledge base have been developed in this paper. Two self-learning models based on pattern comparison: deterministic knowledge and uncertain knowledge self-learning model are presented, while a scene understanding method for intelligent autonomous behavior of equipment is proposed. The research scheme of intelligent autonomous behavior optimization of equipment based on scene understanding and the specific research framework of workpiece machining precision are produced. Finally, focusing on the actual production process of bearing end cover, the flexible automatic production line of bearing end cover is established, the workpiece machining accuracy research based on independent behavior of equipment for CMM and CNC machine tools is preliminarily realized with the help of automatic line control end, it lays a solid foundation for the overall autonomous and intelligent cooperation between the testing area and the processing area. © 2021 Chinese Automation and Computing Society in the UK-CACSUK.

关键词： knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

A Many-Objective Evolutionary Algorithm Assisted by Ideal Hyperplane

SSRN

引用

SSRN 2022年

作者： Zhang, Zhixia Wen, Jie Wang, Hui Cai, Xingjuan Cui, Zhihua Zhang, Wensheng School of Computer Science and Technology Taiyuan University of Science and Technology China School of Information Engineering Nanchang Institute of Technology Nanchang330099 China State Key Laboratory of Intelligent Control and Management of Complex System Institute of Automation Chinese Academy of Sciences China State Key Lab. for Novel Software Technology Nanjing University China

In many-objective optimization problems (MaOPs), it is a difficult task for evolutionary algorithms to balance convergence and diversity while rapidly converging to the Pareto front. As the number of objectives increases, the difficulty of evolutionary algorithms increases with individual selection pressure. To address above problems, we propose a many-objective evolution algorithm assisted by an ideal hyperplane (MaOEA-IH). Firstly, the ideal hyperplane as a reference surface to guide the individual to search the Pareto front, which is established from the extremum of each dimension of the objective space. Secondly, a parallel p -norm mating selection strategy is proposed to improve convergence. In addition, two factors are considered in this strategy: 1) different p -norm are used to measure different spatial scales;2) individual selection uncertainty is defined by incorporating a probabilistic perturbation mechanism. Thirdly, the improved shift-based density estimation strategy is used as the evaluation criterion for environmental selection to improve the convergence and diversity of solution sets and enhance selection pressure. To verify the effectiveness of the proposed algorithm, MAOEA-IH is compared with seven excellent algorithms in three benchmark sets (DTLZ, WFG and MaF). The results show that the proposed MAOEA-IH is highly competitive in solving MaOPs. © 2022, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Novel few-shot learning based fuzzy feature detection algorithms

Novel few-shot learning based fuzzy feature detection algori...

引用

International Conference on Data science and Advanced Analytics (DSAA)

作者： Yun Luo Liangfu Lu Xudong Cui Yan Du Yingying Bi Limin Zhu Christy Jie Liang Faculty of Engineering and Information Technology University of Technology Sydney Australia ICSL Institute of Innovation Science and Sustainability (IISS) Federation University Melbourne Australia School of Mathematics Tianjin University Tianjin China Department of AI Ding-Beijing Intelligent Technology Beijing China Tianjin Key Lab of Retinal Functions and Diseases Tianjin Medical University Tianjin China School of Computer Science University of Technology Sydney Sydney Australia

The Internet of Things (IoT) has significantly enhanced various aspects of our daily lives, including security, health, education, and energy efficiency, among others. Within the realm of IoT, image classification stands as a pivotal technique that has achieved notable success in domains such as facial recognition within security and scene recognition in transportation for traffic analysis. Nonetheless, the challenge emerges when tackling classification tasks with only limited labeled samples available for each category. Conventional machine learning techniques often struggle to attain satisfactory classification results under such circumstances. To address this issue, the concept of few-shot learning has emerged, aiming to achieve effective classification using only a small number of labeled samples. State-of-the-art few-shot learning models have introduced novel frameworks to tackle this problem. However, the inherent ambiguity and uncertainty within data often hinder the performance of classification methods. To overcome this limitation, this paper proposes the integration of fuzzy learning with few-shot learning in the context of feature extraction. The objective is to mitigate data fuzziness and enhance model performance. Leveraging a fuzzy extraction algorithm, we introduce fuzzy prototype networks and a fuzzy graph neural network with fuzzy reasoning. These frameworks are designed to analyze noisy and uncertain data, utilizing convolutional neural networks for feature extraction and applying fuzzy reasoning to capture ambiguity representations for features within each fuzzy set. The SoftMax function is then normalized to serve as a feature weight, effectively constraining the original feature vector. The effectiveness and efficiency of our proposed model are demonstrated through experimental evaluations conducted on various public datasets. The results showcase the model’s capability in addressing the challenges posed by limited labeled data and data uncertai

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization

Towards Feature Distribution Alignment and Diversity Enhance...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Yangcheng Gao Zhao Zhang Richang Hong Haijun Zhang Jicong Fan Shuicheng Yan School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Department of Computer Science Harbin Institute of Technology (Shenzhen) Xili University Town Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China National University of Singapore Singapore

To obtain lower inference latency and less memory footprint of deep neural networks, model quantization has been widely employed in deep model deployment, by converting the floating points to low-precision integers. However, previous methods (such as quantization aware training and post training quantization) require original data for the fine-tuning or calibration of quantized model, which makes them inapplicable to the cases that original data are not accessed due to privacy or security. This gives birth to the data-free quantization method with synthetic data generation. While current data-free quantization methods still suffer from severe performance degradation when quantizing a model into lower bit, caused by the low inter-class separability of semantic features. To this end, we propose a new and effective data-free quantization method termed ClusterQ, which utilizes the feature distribution alignment for synthetic data generation. To obtain high inter-class separability of semantic features, we cluster and align the feature distribution statistics to imitate the distribution of real data, so that the performance degradation is alleviated. Moreover, we incorporate the diversity enhancement to solve class-wise mode collapse. We also employ the exponential moving average to update the centroid of each cluster for further feature distribution improvement. Extensive experiments based on different deep models (e.g., ResNet-18 and MobileNet-V2) over the ImageNet dataset demonstrate that our proposed ClusterQ model obtains state-of-the-art performance.

关键词： Degradation Training Quantization (signal) Semantics Neural networks Memory management Data models

来源：评论

学校读者我要写书评

暂无评论

Cognitive modelling with multilayer networks: Insights, advancements and future challenges

arXiv

引用

arXiv 2022年

作者： Stella, Massimo Citraro, Salvatore Rossetti, Giulio Marinazzo, Daniele Kenett, Yoed N. Vitevitch, Michael S. CogNosco Lab Department of Computer Science University of Exeter Exeter United Kingdom Department of Computer Science University of Pisa Pisa Italy Institute of Information Science and Technologies National Research Council Pisa Italy Faculty of Psychology and Educational Sciences Department of Data Analysis University of Ghent Ghent Belgium Cognitive Complexity Lab Faculty of Industrial Engineering and Management Technion Israel Institute of Technology Israel Department of Psychology University of Kansas LawrenceKS United States

The mental lexicon is a complex cognitive system representing information about the words/concepts that one knows. Decades of psychological experiments have shown that conceptual associations across multiple, interactive cognitive levels can greatly influence word acquisition, storage, and processing. How can semantic, phonological, syntactic, and other types of conceptual associations be mapped within a coherent mathematical framework to study how the mental lexicon works? We here review cognitive multilayer networks as a promising quantitative and interpretative framework for investigating the mental lexicon. Cognitive multilayer networks can map multiple types of information at once, thus capturing how different layers of associations might co-exist within the mental lexicon and influence cognitive processing. This review starts with a gentle introduction to the structure and formalism of multilayer networks. We then discuss quantitative mechanisms of psychological phenomena that could not be observed in single-layer networks and were only unveiled by combining multiple layers of the lexicon: (i) multiplex viability highlights language kernels and facilitative effects of knowledge processing in healthy and clinical populations;(ii) multilayer community detection enables contextual meaning reconstruction depending on psycholinguistic features;(iii) layer analysis can mediate latent interactions of mediation, suppression and facilitation for lexical access. By outlining novel quantitative perspectives where multilayer networks can shed light on cognitive knowledge representations, also in next-generation brain/mind models, we discuss key limitations and promising directions for cutting-edge future research. © 2022, CC BY.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Op2Vec: An Opcode Embedding Technique and Dataset Design for End-to-End Detection of Android Malware

arXiv

引用

arXiv 2021年

作者： Khan, Kaleem Nawaz Ullah, Najeeb Ali, Sikandar Khan, Muhammad Salman Nauman, Mohammad Ghani, Anwar Department of Computer Science University of Engineering and Technology Mardan Pakistan Department of Computer Science and Technology University of Swat Pakistan AI in Healthcare Intelligent Information Processing Lab National Center of Artificial Intelligence UET Peshawar Pakistan University of Engineering and Technology Peshawar Pakistan Department of Computer Science National University of Computer and Emerging Sciences Peshawar Pakistan Department of Computer Science and Software Engineering International Islamic University Islamabad Pakistan

Android is one of the leading operating systems for smart phones in terms of market share and usage. Unfortunately, it is also an appealing target for attackers to compromise its security through malicious applications. To tackle this issue, domain experts and researchers are trying different techniques to stop such attacks. All the attempts of securing Android platform are somewhat successful. However, existing detection techniques have severe shortcomings, including the cumbersome process of feature engineering. Designing representative features require expert domain knowledge. There is a need for minimizing human experts' intervention by circumventing handcrafted feature engineering. Deep learning could be exploited by extracting deep features automatically. Previous work has shown that operational codes (opcodes) of executables provide key information to be used with deep learning models for detection process of malicious applications. The only challenge is to feed opcodes information to deep learning models. Existing techniques use one-hot encoding to tackle the challenge. However, the one-hot encoding scheme has severe limitations. In this paper, we introduce;(1) a novel technique for opcodes embedding, which we name Op2Vec, (2) based on the learned Op2Vec we have developed a dataset for end-to-end detection of android malware. Introducing the end-to-end Android malware detection technique avoids expert-intensive handcrafted features extraction, and ensures automation. Some of the recent deep learning-based techniques showed significantly improved results when tested with the proposed approach and achieved an average detection accuracy of 97.47%, precision of 0.976 and F1 score of 0.979. Copyright © 2021, The Authors. All rights reserved.

关键词： Android (operating system)

来源：评论

学校读者我要写书评

暂无评论

Model-Driven Deep Learning for Non-Coherent Massive Machine-Type Communications

arXiv

引用

arXiv 2023年

作者： Ma, Zhe Wu, Wen Gao, Feifei Shen, Xuemin The Institute for Artificial Intelligence Tsinghua University State Key Lab of Intelligent Technologies and Systems Beijing National Research Center for Information Science and Technology Department of Automation Tsinghua University Beijing100084 China The Frontier Research Center Peng Cheng Laboratory Guangdong Shenzhen518055 China The Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada

In this paper, we investigate the joint device activity and data detection in massive machine-type communications (mMTC) with a one-phase non-coherent scheme, where data bits are embedded in the pilot sequences and the base station simultaneously detects active devices and their embedded data bits without explicit channel estimation. Due to the correlated sparsity pattern introduced by the noncoherent transmission scheme, the traditional approximate message passing (AMP) algorithm cannot achieve satisfactory performance. Therefore, we propose a deep learning (DL) modified AMP network (DL-mAMPnet) that enhances the detection performance by effectively exploiting the pilot activity correlation. The DL-mAMPnet is constructed by unfolding the AMP algorithm into a feedforward neural network, which combines the principled mathematical model of the AMP algorithm with the powerful learning capability, thereby benefiting from the advantages of both techniques. Trainable parameters are introduced in the DL-mAMPnet to approximate the correlated sparsity pattern and the large-scale fading coefficient. Moreover, a refinement module is designed to further advance the performance by utilizing the spatial feature caused by the correlated sparsity pattern. Simulation results demonstrate that the proposed DL-mAMPnet can significantly outperform traditional algorithms in terms of the symbol error rate performance. © 2023, CC BY-NC-SA.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Universal semi-supervised learning 21

Universal semi-supervised learning

引用

Proceedings of the 35th International Conference on Neural information Processing Systems

作者： Zhuo Huang Chao Xue Bo Han Jian Yang Chen Gong PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology and JD Explore Academy JD Explore Academy Department of Computer Science Hong Kong Baptist University PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology

ISBN: (纸本)9781713845393

Universal Semi-Supervised Learning (UniSSL) aims to solve the open-set problem where both the class distribution (i.e., class set) and feature distribution (i.e., feature domain) are different between labeled dataset and unlabeled dataset. Such a problem seriously hinders the realistic landing of classical SSL. Different from the existing SSL methods targeting at the open-set problem that only study one certain scenario of class distribution mismatch and ignore the feature distribution mismatch, we consider a more general case where a mismatch exists in both class and feature distribution. In this case, we propose a "Class-shAring data detection and Feature Adaptation" (CAFA) framework which requires no prior knowledge of the class relationship between the labeled dataset and unlabeled dataset. Particularly, CAFA utilizes a novel scoring strategy to detect the data in the shared class set. Then, it conducts domain adaptation to fully exploit the value of the detected class-sharing data for better semi-supervised consistency training. Exhaustive experiments on several benchmark datasets show the effectiveness of our method in tackling open-set problems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey for Hyperspectral Image Classification: The Evolution from Conventional to Transformers and Mamba Models

arXiv

引用

arXiv 2024年

作者： Ahmad, Muhammad Distefano, Salvatore Khan, Adil Mehmood Mazzara, Manuel Li, Chenyu Li, Hao Aryal, Jagannath Ding, Yao Vivone, Gemine Hong, Danfeng Department of Computer Science National University of Computer and Emerging Sciences Islamabad Pakistan Dipartimento di Matematica e Informatica-MIFT University of Messina Messina98121 Italy School of Computer Science University of Hull HullHU6 7RX United Kingdom Institute of Software Development and Engineering Innopolis University Innopolis420500 Russia Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Big Geospatial Data Management Technical University of Munich Munich85521 Germany Department of Infrastructure Engineering University of Melbourne ParkvilleVIC Australia Intelligent Control Laboratory PLA Rocket Force University of Engineering Xi’an710025 China Institute of Methodologies for Environmental Analysis National Research Council Tito85050 Italy School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China

Hyperspectral Image Classification (HSC) presents significant challenges owing to the high dimensionality and intricate nature of Hyperspectral (HS) data. While traditional Machine Learning (TML) approaches have demonstrated effectiveness, they often encounter substantial obstacles in real-world applications, including the variability of optimal feature sets, subjectivity in human-driven design, inherent biases, and methodological limitations. Specifically, TML suffers from the curse of dimensionality, difficulties in feature selection and extraction, insufficient consideration of spatial information, limited robustness against noise, scalability issues, and inadequate adaptability to complex data distributions. In recent years, Deep Learning (DL) techniques have emerged as robust solutions to address these challenges. This survey offers a comprehensive overview of current trends and future prospects in HSC, emphasizing advancements from DL models to the increasing adoption of Transformer and Mamba Model architectures. We systematically review key concepts, methodologies, and state-of-the-art approaches in DL for HSC. Furthermore, we investigate the potential of Transformer-based models and the Mamba Model in HSC, detailing their advantages and challenges. Emerging trends in HSC are explored, including in-depth discussions on Explainable AI and Interoperability concepts, alongside Diffusion Models for image denoising, feature extraction, and image fusion. To substantiate the efficacy of various conventional DL models, Transformers, and the Mamba Model, comprehensive experimental results were conducted on three HS datasets, yielding notable accuracies: 99.94% on Pavia University, 99.41% on Indian Pines, and 99.97% on the University of Houston dataset. Additionally, we identify several open challenges and pertinent research questions in the field of HSC. Finally, we outline future research directions and potential applications aimed at enhancing the accuracy and effic

关键词： Convolutional neural networks

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：