检索结果-南通市图书馆

MAML^(2):meta reinforcement learning via Meta-learning for task categories

Frontiers of Computer Science 2023年第4期17卷 57-67页

作者： Qiming FU Zhechao WANG Nengwei FANG Bin XING Xiao ZHANG Jianping CHEN School of Electronics and Information Engineering Suzhou University of Science and TechnologySuzhou 215009China Chongqing Industrial Big Data Innovation Center Co.Ltd. Chongqing 404100China School of Medical Informatics Xuzhou Medical UniversityXuzhou 221004China School of Architecture and Urban Planning Suzhou University of Science and TechnologySuzhou 215009China

Meta-learning has been widely applied to solving few-shot reinforcement learning problems,where we hope to obtain an agent that can learn quickly in a new task.However,these algorithms often ignore some isolated tasks in pursuit of the average performance,which may result in negative adaptation in these isolated tasks,and they usually need sufficient learning in a stationary task distribution.In this paper,our algorithm presents a hierarchical framework of double Meta-learning,and the whole framework includes classification,Meta-learning,and re-adaptation.Firstly,in the classification process,we classify tasks into several task subsets,considered as some categories of tasks,by learned parameters of each task,which can separate out some isolated tasks thereafter.Secondly,in the Meta-learning process,we learn category parameters in all subsets via Meta-learning.Simultaneously,based on the gradient of each category parameter in each subset,we use Meta-learning again to learn a new metaparameter related to the whole task set,which can be used as an initial parameter for the new task.Finally,in the re-adaption process,we adapt the parameter of the new task with two steps,by the meta-parameter and the appropriate category parameter successively.Experimentally,we demonstrate our algorithm prevents the agent from negative adaptation without losing the average performance for the whole task set.Additionally,our algorithm presents a more rapid adaptation process within readaptation.Moreover,we show the good performance of our algorithm with fewer samples as the agent is exposed to an online Meta-learning setting.

关键词： Meta-learning reinforcement learning few-shot learning negative adaptation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Augmentation-based discriminative Meta-learning for cross-machine few-shot fault diagnosis

引用

Science China(Technological Sciences) 2023年第6期66卷 1698-1716页

作者： XIA PengCheng HUANG YiXiang WANG YuXiang LIU ChengLiang LIU Jie State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong UniversityShanghai 200240China MoE Key Lab of Artificial Intelligence AI InstituteShanghai Jiao Tong UniversityShanghai 200240China Department of Mechanical and Aerospace Engineering Carleton UniversityOttawa ON K1S 5B6Canada

Deep learning methods have demonstrated promising performance in fault diagnosis tasks.Although the scarcity of data in industrial scenarios limits the practical application of such methods,transfer learning effectively tackles this issue through crossmachine knowledge transfer.Nevertheless,the cross-machine few-shot problem,which is a more general industrial scenario,has been rarely investigated.Existing studies have not considered the cross-machine domain shift problem,which results in poor testing performance.This paper proposes an augmentation-based discriminative Meta-learning method to address this issue.In the meta-training process,signal transformation is proposed to increase the meta-task diversity for more robust feature learning,and multi-scale learning is combined for more adaptive feature embedding.In the meta-testing process,limited labeled fault information is used to promote model generalization in the target domain through quasi-meta-training based on data augmentation.Furthermore,a novel hyperbolic prototypical loss is proposed for more discriminative feature representation and separable category prototypes by designing a hyperbolic decision boundary.Cross-machine few-shot diagnosis experiments were conducted using three datasets from different machines,namely,the bearing,motor,and gear datasets.The effectiveness of the proposed method was verified through ablation and comparison studies.

关键词： fault diagnosis few-shot learning Meta-learning data augmentation cross-machine discriminative loss

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Few-shot working condition recognition of a sucker-rod pumping system based on a 4-dimensional time-frequency signature and Meta-learning convolutional shrinkage neural network

引用

Petroleum Science 2023年第2期20卷 1142-1154页

作者： Yun-Peng He Chuan-Zhi Zang Peng Zeng Ming-Xin Wang Qing-Wei Dong Guang-Xi Wan Xiao-Ting Dong State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyangLiaoning 110016China Key Laboratory of Networked Control Systems Chinese Academy of SciencesShenyangLiaoning 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyangLiaoning 110169China University of Chinese Academy of Sciences Beijing100049China Shenyang University of Technology ShenyangLiaoning 110870China School of Automation and Electrical Engineering Shenyang Ligong UniversityShenyangLiaoning 110159China

The accurate and intelligent identification of the working conditions of a sucker-rod pumping system is necessary. As onshore oil extraction gradually enters its mid-to late-stage, the cost required to train a deep learning working condition recognition model for pumping wells by obtaining enough new working condition samples is expensive. For the few-shot problem and large calculation issues of new working conditions of oil wells, a working condition recognition method for pumping unit wells based on a 4-dimensional time-frequency signature (4D-TFS) and Meta-learning convolutional shrinkage neural network (ML-CSNN) is proposed. First, the measured pumping unit well workup data are converted into 4D-TFS data, and the initial feature extraction task is performed while compressing the data. Subsequently, a convolutional shrinkage neural network (CSNN) with a specific structure that can ablate low-frequency features is designed to extract working conditions features. Finally, a Meta-learning fine-tuning framework for learning the network parameters that are susceptible to task changes is merged into the CSNN to solve the few-shot issue. The results of the experiments demonstrate that the trained ML-CSNN has good recognition accuracy and generalization ability for few-shot working condition recognition. More specifically, in the case of lower computational complexity, only few-shot samples are needed to fine-tune the network parameters, and the model can be quickly adapted to new classes of well conditions.

关键词： Few-shot learning Indicator diagram Meta-learning Soft thresholding Sucker-rod pumping system Time–frequency signature Working condition recognition

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Crop Disease Recognition Based on Improved Model-Agnostic Meta-learning

引用

Computers, Materials & Continua 2023年第6期75卷 6101-6118页

作者： Xiuli Si Biao Hong Yuanhui Hu Lidong Chu College of Information Technology Jilin Agricultural UniversityChangchun130118China College of Engineering and Technology Jilin Agricultural UniversityChangchun130118China

Currently,one of the most severe problems in the agricultural industry is the effect of diseases and pests on global crop production and economic development.Therefore,further research in the field of crop disease and pest detection is necessary to address the mentioned problem.Aiming to identify the diseased crops and insect pests timely and accurately and perform appropriate prevention measures to reduce the associated losses,this article proposes a Model-Agnostic Meta-learning(MAML)attention model based on the Meta-learning paradigm.The proposed model combines Meta-learning with basic learning and adopts an Efficient Channel Attention(ECA)mod-ule.The module follows the local cross-channel interactive strategy of non-dimensional reduction to strengthen the weight parameters corresponding to certain disease characteristics.The proposed Meta-learning-based algorithm has the advantage of strong generalization capability and,by integrating the ECA module in the original model,can achieve more efficient detection in new tasks.The proposed model is verified by experiments,and the experimental results show that compared with the original MAML model,the proposed improved MAML-Attention model has a better performance by 1.8–9.31 percentage points in different classification tasks;the maximum accuracy is increased by 1.15–8.2 percentage points.The experimental results verify the strong generalization ability and good robustness of the proposed MAML-Attention model.Compared to the other few-shot methods,the proposed MAML-Attention performs better.

关键词： Meta-learning disease image recognition deep learning attention mechanism

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Scene-adaptive crowd counting method based on meta learning with dual-input network DMNet

引用

Frontiers of Computer Science 2023年第1期17卷 91-100页

作者： Haoyu ZHAO Weidong MIN Jianqiang XU Qi WANG Yi ZOU Qiyan FU School of Information Engineering Nanchang UniversityNanchang 330031China School of Software Nanchang UniversityNanchang 330047China Jiangxi Key Laboratory of Smart City Nanchang 330047China

Crowd counting is recently becoming a hot research topic, which aims to count the number of the people in different crowded scenes. Existing methods are mainly based on training-testing pattern and rely on large data training, which fails to accurately count the crowd in real-world scenes because of the limitation of model’s generalization capability. To alleviate this issue, a scene-adaptive crowd counting method based on Meta-learning with Dual-illumination Merging Network (DMNet) is proposed in this paper. The proposed method based on learning-to-learn and few-shot learning is able to adapt different scenes which only contain a few labeled images. To generate high quality density map and count the crowd in low-lighting scene, the DMNet is proposed, which contains Multi-scale Feature Extraction module and Element-wise Fusion Module. The Multi-scale Feature Extraction module is used to extract the image feature by multi-scale convolutions, which helps to improve network accuracy. The Element-wise Fusion module fuses the low-lighting feature and illumination-enhanced feature, which supplements the missing illumination in low-lighting environments. Experimental results on benchmarks, WorldExpo’10, DISCO, USCD, and Mall, show that the proposed method outperforms the existing state-of-the-art methods in accuracy and gets satisfied results.

关键词： crowd counting Meta-learning scene-adaptive Dual-illumination Merging Network

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Application of Meta-learning in cyberspace security:a survey

引用

Digital Communications and Networks 2023年第1期9卷 67-78页

作者： Aimin Yang Chaomeng Lu Jie Li Xiangdong Huang Tianhao Ji Xichang Li Yichao Sheng Hebei Key Laboratory of Data Science and Application North China University of Science and TechnologyTangshan063000China Hebei Engineering Research Center for the Intelligentization of Iron Ore Optimization and Ironmaking Raw Materials Preparation Processes North China University of Science and TechnologyTangshan063000China The Key Laboratory of Engineering Computing in Tangshan City North China University of Science and TechnologyTangshan063000China

In recent years,machine learning has made great progress in intrusion detection,network protection,anomaly detection,and other issues in cyberspace.However,these traditional machine learning algorithms usually require a lot of data to learn and have a low recognition rate for unknown attacks.Among them,“one-shot learning”,“few-shot learning”,and“zero-shot learning”are challenges that cannot be ignored for traditional machine learning.The more intractable problem in cyberspace security is the changeable attack mode.When a new attack mode appears,there are few or even zero samples that can be learned.Meta-learning comes from imitating human problem-solving methods as humans can quickly learn unknown things based on their existing knowledge when learning.Its purpose is to quickly obtain a model with high accuracy and strong generalization through less data training.This article first divides the Meta-learning model into five research directions based on different principles of use.They are model-based,metric-based,optimization-based,online-learning-based,or stacked ensemble-based.Then,the current problems in the field of cyberspace security are categorized into three branches:cyber security,information security,and artificial intelligence security according to different perspectives.Then,the application research results of various Meta-learning models on these three branches are reviewed.At the same time,based on the characteristics of strong generalization,evolution,and scalability of Meta-learning,we contrast and summarize its advantages in solving problems.Finally,the prospect of future deep application of Meta-learning in the field of cyberspace security is summarized.

关键词： Meta-learning Cyberspace security Machine learning Few-shot learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Smoother manifold for graph Meta-learning

引用

High Technology Letters 2022年第1期28卷 48-55页

作者：赵文仓 WANG Chunxin XU Changkai College of Automation and Electronic Engineering Qingdao University of Science and TechnologyQingdao 266061P.R.China

Meta-learning provides a framework for the possibility of mimicking artificial intelligence.How-ever,data distribution of the training set fails to be consistent with the one of the testing set as the limited domain differences among them.These factors often result in poor generalization in existing Meta-learning models.In this work,a novel smoother manifold for graph Meta-learning(SGML)is proposed,which derives the similarity parameters of node features from the relationship between nodes and edges in the graph structure,and then utilizes the similarity parameters to yield smoother manifold through embedded propagation module.Smoother manifold can naturally filter out noise from the most important components when generalizing the local mapping relationship to the global.Besides suiting for generalizing on unseen low data issues,the framework is capable to easily perform transductive inference.Experimental results on MiniImageNet and TieredImageNet consistently show that applying SGML to supervised and semi-supervised classification can improve the performance in reducing the noise of domain shift representation.

关键词： Meta-learning smoother manifold similarity parameter graph structure

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

meta-BN Net for few-shot learning

引用

Frontiers of Computer Science 2023年第1期17卷 73-80页

作者： Wei GAO Mingwen SHAO Jun SHU Xinkai ZHUANG School of Computer Science China University of PetroleumQingdao 266580China School of Mathematics and Statistics Xi’an Jiaotong UniversityXi’an 710049China

In this paper, we propose a lightweight network with an adaptive batch normalization module, called meta-BN Net, for few-shot classification. Unlike existing few-shot learning methods, which consist of complex models or algorithms, our approach extends batch normalization, an essential part of current deep neural network training, whose potential has not been fully explored. In particular, a meta-module is introduced to learn to generate more powerful affine transformation parameters, known as and , in the batch normalization layer adaptively so that the representation ability of batch normalization can be activated. The experimental results on miniImageNet demonstrate that meta-BN Net not only outperforms the baseline methods at a large margin but also is competitive with recent state-of-the-art few-shot learning methods. We also conduct experiments on Fewshot-CIFAR100 and CUB datasets, and the results show that our approach is effective to boost the performance of weak baseline networks. We believe our findings can motivate to explore the undiscovered capacity of base components in a neural network as well as more efficient few-shot learning methods.

关键词： Meta-learning few-shot learning batch normalization

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Improving Meta-learning model via meta-contrastive loss

引用

Frontiers of Computer Science 2022年第5期16卷 107-113页

作者： Pinzhuo TIAN Yang GAO Department of Computer Science and Technology Nanjing UniversityJiangsu 210023China

Recently,addressing the few-shot learning issue with Meta-learning framework achieves great success.As we know,regularization is a powerful technique and widely used to improve machine learning algorithms.However,rare research focuses on designing appropriate meta-regularizations to further improve the generalization of Meta-learning models in few-shot learning.In this paper,we propose a novel metacontrastive loss that can be regarded as a regularization to fill this gap.The motivation of our method depends on the thought that the limited data in few-shot learning is just a small part of data sampled from the whole data distribution,and could lead to various bias representations of the whole data because of the different sampling parts.Thus,the models trained by a few training data(support set)and test data(query set)might misalign in the model space,making the model learned on the support set can not generalize well on the query data.The proposed meta-contrastive loss is designed to align the models of support and query sets to overcome this problem.The performance of the Meta-learning model in few-shot learning can be improved.Extensive experiments demonstrate that our method can improve the performance of different gradientbased Meta-learning models in various learning problems,e.g.,few-shot regression and classification.

关键词： Meta-learning few-shot learning metaregularization deep learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Leveraging Continuous Prompt for Few-Shot Named Entity Recognition in Electric Power Domain with Meta-learning

引用

Data Intelligence 2023年第2期5卷 494-509页

作者： Yang Yu Wei He Yu-meng Kang You-lang Ji Metrology Center State Grid Jiangsu Market Service Center Nanjing Jiangsu 210019China

Conventional named entity recognition methods usually assume that the model can be trained with sufficient annotated data to obtain good recognition results.However,in Chinese named entity recognition in the electric power domain,existing methods still face the challenges of lack of annotated data and new entities of unseen types.To address these challenges,this paper proposes a Meta-learning-based continuous cue adjustment method.A generative pre-trained language model is used so that it does not change its own model structure when dealing with new entity types.To guide the pre-trained model to make full use of its own latent knowledge,a vector of learnable parameters is set as a cue to compensate for the lack of training data.In order to further improve the model's few-shot learning capability,a Meta-learning strategy is used to train the model.Experimental results show that the proposed approach achieves the best results in a few-shot electric Chinese power named entity recognition dataset compared to several traditional named entity approaches.

关键词： Named Entity Recognition Pre-trained model Prompt-Tuning Meta-learning Few-Shot

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：