检索结果-内蒙古大学图书馆

18th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2023

作者： Zhou, Erhao Wang, Guanjin Wang, Shitong School of Information Technology Murdoch University Australia School of AI and Computer Science Jiangnan University Wuxi China TaiHu Univ. Key Construction Lab. of IoT Application Technologies Wuxi China

ISBN: (纸本)9798350318401

With the help of the conditional mean, the mathematically equivalent bridge between a Gaussian mixture model (GMM) and a Takagi-Sugeno-Kang (TSK) fuzzy system has been built to form a GMM-based fuzzy system so as to share mutual support for their respective training from rich achievements about GMM and fuzzy system. However, only the conditional mean without the consideration of stability (i.e., conditional variance) may perhaps hinder the modeling performance of the GMM-based fuzzy system, especially for noisy data scenarios. In this study, with strict mathematical derivations, it is revealed that the stability of a GMM-based fuzzy system depends on the three factors, i.e., stability of each fuzzy rule, stability of each input/output subspace associated with each fuzzy rule, and weighted stability of all fuzzy rules and their input/output subspaces. Accordingly, based on the derived result about the above stabilities, the training method of the proposed EGMM-based (Enhanced GMM-based) TSK fuzzy system, which considers both accuracy and stability is developed to improve the modeling performance of the original GMM-based TSK fuzzy system by optimizing the GMM's parameters therein. The effectiveness of the proposed training method is manifested by the experimental results on 10 real regression datasets. © 2023 IEEE.

关键词： Fuzzy rules

来源：评论

学校读者我要写书评

暂无评论

Lifting up Imbalanced Data Classification to SVM Based Ensemble Level on Oversampling Feature Spaces 16

Lifting up Imbalanced Data Classification to SVM Based Ensem...

引用

16th IEEE International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2021

作者： Zhang, Jin Wang, Shitong Jiangnan University School of Artificial Intelligence and Computer Science Wuxi China Jiangsu Key Construction Lab. of IoT Application Technologies JiangSu China

ISBN: (纸本)9781665405539

The design of supervised machine learning algorithms assumes that the training data are balanced. In terms of industrial machinery failures and medical patient detection reports, such data distributions are generally imbalanced. This type of algorithm has a poor adaptability to this type of data. In response to this problem, in this paper, an imbalanced data classification algorithm from the ensemble level is proposed, which maps the original space to multiple different feature spaces to increase the generalization ability of the ensemble classifier. To ensure the generalization ability of a single classifier, a boundary densification algorithm that densifies majority class boundaries and controls the bias of the decision plane, and can also deal with the classification problem of imbalanced datasets, is also proposed. Experimental results show that, compared with other imbalanced classification algorithms, the oversampling algorithm of the ensemble-level kernel space proposed in this study performs better in imbalanced data classification. © 2021 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

LIPT: Latency-aware Image Processing Transformer

引用

IEEE Transactions on Image Processing 2025年 34卷 3056-3069页

作者： Qiao, Junbo Li, Wei Xie, Haizhen Chen, Hanting Hu, Jie Lin, Shaohui Han, Jungong East China Normal University School of Computer Science and Technology Shanghai200062 China Huawei Technologies Ltd Huawei Noah’s Ark Lab Shanghai China Ministry of Education Key Laboratory of Advanced Theory and Application in Statistics and Data Science China Tsinghua University Department of Automation Beijing100084 China

Transformer is leading a trend in the field of image processing. While existing lightweight image processing transformers have achieved notable success, they primarily focus on reducing FLOPs (floating-point operations) or the number of parameters, rather than on practical inference acceleration. In this paper, we present a latency-aware image processing transformer, termed LIPT. We devise the low-latency proportion LIPT block that substitutes memory-intensive operators with the combination of self-attention and convolutions to achieve practical speedup. Specifically, we propose a novel non-volatile sparse masking self-attention (NVSM-SA) that utilizes a pre-computing sparse mask to capture contextual information from a larger window with no extra computation overload. Besides, a high-frequency reparameterization module (HRM) is proposed to make LIPT block reparameterization friendly, enhancing the model’s ability to reconstruct fine details. Extensive experiments on multiple image processing tasks (e.g., image super-resolution (SR), JPEG artifact reduction, and image denoising) demonstrate the superiority of LIPT on both latency and PSNR. LIPT achieves real-time GPU inference with state-of-the-art performance on multiple image SR benchmarks. © 1992-2012 IEEE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Improved Training of GMM-Based TSK Fuzzy System from Stability Perspective

Improved Training of GMM-Based TSK Fuzzy System from Stabili...

引用

International Conference on Intelligent System and Knowledge Engineering, ISKE

作者： Erhao Zhou Guanjin Wang Shitong Wang School of AI and Computer Science Jiangnan University Wuxi China School of Information Technology Murdoch University Australia Key Construction Lab. of IoT Application Technologies TaiHu Univ. Wuxi China

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model-enhanced vector index 23

Model-enhanced vector index

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Hailin Zhang Yujing Wang Qi Chen Ruiheng Chang Ting Zhang Ziming Miao Yingyan Hou Yang Ding Xupeng Miao Haonan Wang Bochen Pang Yuefeng Zhan Hao Sun Weiwei Deng Qi Zhang Fan Yang Xing Xie Mao Yang Bin Cui School of Computer Science & Key Lab of High Confidence Software Technologies Peking University and Microsoft Microsoft Microsoft and Aerospace Information Research Institute & Key Laboratory of Target Cognition and Application Technology Chinese Academy of Sciences Microsoft and Institute of Information Engineering Chinese Academy of Sciences Carnegie Mellon University National University of Singapore School of Computer Science & Key Lab of High Confidence Software Technologies Peking University and National Engineering Laboratory for Big Data Analysis and Applications Peking University

Embedding-based retrieval methods construct vector indices to search for document representations that are most similar to the query representations. They are widely used in document retrieval due to low latency and decent recall performance. Recent research indicates that deep retrieval solutions offer better model quality, but are hindered by unacceptable serving latency and the inability to support document updates. In this paper, we aim to enhance the vector index with end-to-end deep generative models, leveraging the differentiable advantages of deep retrieval models while maintaining desirable serving efficiency. We propose Model-enhanced Vector Index (MEVI), a differentiable model-enhanced index empowered by a twin-tower representation model. MEVI leverages a Residual Quantization (RQ) codebook to bridge the sequence-to-sequence deep retrieval and embedding-based models. To substantially reduce the inference time, instead of decoding the unique document ids in long sequential steps, we first generate some semantic virtual cluster ids of candidate documents in a small number of steps, and then leverage the well-adapted embedding vectors to further perform a fine-grained search for the relevant documents in the candidate virtual clusters. We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NEGAR: Network Embedding Guided Architecture Recovery for Software Systems

NEGAR: Network Embedding Guided Architecture Recovery for So...

引用

Asia-Pacific Conference on Software Engineering

作者： Jiayi Chen Zhixing Wang Yuchen Jiang Jun Pang Tian Zhang Minxue Pan Jianwen Sun State Key Lab for Novel Software Technology Nanjing University Nanjing China Department of Computer Science University of Luxembourg Esch-sur-Alzette Luxembourg Huawei Technologies Software Engineering Application Technology Lab Shenzhen China

ISBN: (纸本)9781665455381

With their rapid development, the scale and complexity of software systems are rapidly growing. Identifying and organizing files of similar functionality into the same module, called architecture recovery, contributes to the maintainability of a software system. However, manual architecture recovery on large-sized software requires unbearable costs. Hence a lot of automatic algorithms have been proposed in recent years. However, current algorithms’ accuracy is still insufficient to support practical applications. To improve the accuracy of architecture recovery, this work proposes a novel algorithm, NEGAR, which leverages random walks to extract latent graphic information from the dependency graph of files in the software system and learn the node representation for clustering. The proposed algorithm NEGAR has been comprehensively evaluated on three medium-sized and two large-sized software systems, as well as a super large-sized software system, in terms of four widely-used metrics. The experimental results demonstrate the outstanding accuracy and excellent scalability of NEGAR.

关键词： Measurement Codes Scalability Software algorithms Semantics Clustering algorithms computer architecture

来源：评论

学校读者我要写书评

暂无评论

Lifting up Imbalanced Data Classification to SVM Based Ensemble Level on Oversampling Feature Spaces

Lifting up Imbalanced Data Classification to SVM Based Ensem...

引用

International Conference on Intelligent System and Knowledge Engineering, ISKE

作者： Jin Zhang Shitong Wang School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Jiangsu Key Construction Lab. of IoT Application Technologies JiangSu China

ISBN: (纸本)9781665405546

关键词： Support vector machines Knowledge engineering Machine learning algorithms Training data Machine learning Aerospace electronics Robustness

来源：评论

学校读者我要写书评

暂无评论

Model-enhanced Vector Index

arXiv

引用

arXiv 2023年

作者： Zhang, Hailin Wang, Yujing Chen, Qi Chang, Ruiheng Zhang, Ting Miao, Ziming Hou, Yingyan Ding, Yang Miao, Xupeng Wang, Haonan Pang, Bochen Zhan, Yuefeng Sun, Hao Deng, Weiwei Zhang, Qi Yang, Fan Xie, Xing Yang, Mao Cui, Bin School of Computer Science Key Lab of High Confidence Software Technologies Peking University China Microsoft United States Aerospace Information Research Institute Key Laboratory of Target Cognition and Application Technology Chinese Academy of Sciences China Institute of Information Engineering Chinese Academy of Sciences China Carnegie Mellon University United States National University of Singapore Singapore National Engineering Laboratory for Big Data Analysis and Applications Peking University China

Embedding-based retrieval methods construct vector indices to search for document representations that are most similar to the query representations. They are widely used in document retrieval due to low latency and decent recall performance. Recent research indicates that deep retrieval solutions offer better model quality, but are hindered by unacceptable serving latency and the inability to support document updates. In this paper, we aim to enhance the vector index with endto- end deep generative models, leveraging the differentiable advantages of deep retrieval models while maintaining desirable serving efficiency. We propose Modelenhanced Vector Index (MEVI), a differentiable model-enhanced index empowered by a twin-tower representation model. MEVI leverages a Residual Quantization (RQ) codebook to bridge the sequence-to-sequence deep retrieval and embeddingbased models. To substantially reduce the inference time, instead of decoding the unique document ids in long sequential steps, we first generate some semantic virtual cluster ids of candidate documents in a small number of steps, and then leverage the well-adapted embedding vectors to further perform a fine-grained search for the relevant documents in the candidate virtual clusters. We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Multimodal Dialogue Systems via Capturing Context-aware Dependencies of Semantic Elements 20

Multimodal Dialogue Systems via Capturing Context-aware Depe...

引用

28th ACM International Conference on Multimedia, MM 2020

作者： He, Weidong Li, Zhi Lu, Dongcai Chen, Enhong Huai, Baoxing Yuan, Jing Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China School of Data Science University of Science and Technology of China China HUAWEI Technologies Hangzhou China

ISBN: (纸本)9781450379885

Recently, multimodal dialogue systems have engaged increasing attention in several domains such as retail, travel, etc. In spite of the promising performance of pioneer works, existing studies usually focus on utterance-level semantic representations with hierarchical structures, which ignore the context-aware dependencies of multimodal semantic elements, i.e., words and images. Moreover, when integrating the visual content, they only consider images of the current turn, leaving out ones of previous turns as well as their ordinal information. To address these issues, we propose a Multimodal diAlogue systems with semanTic Elements, MATE for short. Specifically, we unfold the multimodal inputs and devise a Multimodal Element-level Encoder to obtain the semantic representation at element-level. Besides, we take into consideration all images that might be relevant to the current turn and inject the sequential characteristics of images through position encoding. Finally, we make comprehensive experiments on a public multimodal dialogue dataset in the retail domain, and improve the BLUE-4 score by 9.49, and NIST score by 1.8469 compared with state-of-the-art methods. © 2020 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Sentiment classification method for Chinese and Vietnamese bilingual news sentence based on convolution neural network

Sentiment classification method for Chinese and Vietnamese b...

引用

International Conference on Mechatronics and Intelligent Robotics, ICMIR 2018

作者： He, Xiaoxu Gao, Shengxiang Yu, Zhengtao Liu, Shulong Hong, Xudong Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Key Lab of Computer Technologies Application of Yunnan Province Kunming University of Science and Technology Kunming650500 China

ISBN: (纸本)9783030002138

Sentiment classification of the Chinese and Vietnamese news is important to analysis public opinion of Chinese and Vietnamese. For cross-lingual sentiment analysis, this paper studies the method of sentiment analysis for Chinese and Vietnamese bilingual news sentence based on convolution neural network (CNN). Firstly, collect Chinese and Vietnamese news data from Internet, use the data collected to train word vector. Secondly, employ the pre-trained word vector and bilingual lexicon to project the Chinese news labeled data to bilingual word vector space, the problem of the lack of annotated corpus in Vietnamese is solved in a certain level. Finally, using convolution neural network to make cross-lingual sentiment classification. Experiment result shows that the F score of Vietnamese news classification has reached 86%. Compared with the traditional methods, the proposed method does not need to construct sentiment lexicon and perform feature extraction, and the performance of cross-lingual sentiment classification is also remarkable. © Springer Nature Switzerland AG 2019.

关键词： Sentiment analysis

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：