检索结果-内蒙古大学图书馆

Dynamic Mask Curriculum Learning for Non-Autoregressive Neural Machine Translation 1

18th China Conference on Machine Translation, CCMT 2022

作者： Wang, Yisong Hou, Hongxu Sun, Shuo Wu, Nier Jian, Weichen Yang, Zongheng Wang, Pengcong National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology College of Computer Science Inner Mongolia University Hohhot China

ISBN: (数字)9789811979606

ISBN: (纸本)9789811979590

Non-autoregressive neural machine translation is gradually becoming a research hotspot due to its advantages of fast decoding. However, the increase of decoding speed is often accompanied by the loss of model performance. The main reason is that the target language information obtained at the decoder side is insufficient, and the mandatory parallel decoding leads to a large number of mistranslation and missing translation problems. In order to solve the problem of insufficient target language information, this paper proposes a dynamic mask curriculum learning approach to provide target side language information to the model. The target side self-attention layer is added in the pre-training phase to capture the target side information and adjust the amount of information input at any time by way of curriculum learning. The fine-tuning and inference phases disable the module in the same way as the normal NAT model. In this paper, we experiment on two translation datasets of WMT16, and the BLEU improvement reaches 4.4 without speed reduction. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Self-Injection Locked Nonlinear Brillouin Laser in Chalcogenide Microresonators 16

Self-Injection Locked Nonlinear Brillouin Laser in Chalcogen...

引用

16th Pacific Rim Conference on Lasers and Electro-Optics, CLEO-PR 2024

作者： Chen, Wendong Wang, Zifu Xia, Di Li, Yufei Li, Zhaohui Zhang, Bin School of Electrical and Information Technology Sun Yat-sen University Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Guangzhou510275 China Sun Yat-sen University Key Laboratory of Optoelectronic Materials and Technologies Guangzhou510275 China Zhuhai519000 China

We demonstrate a self-injection locked nonlinear Brillouin laser in an integrated chalcogenide microresonator with an intrinsic linewidth of 1 Hz and 50 dB frequency noise suppression compared to a free-running DFB la... 详细信息

ISBN: (纸本)9798350372076

关键词： Microresonators

来源：评论

学校读者我要写书评

暂无评论

Dynamic Negative Example Construction for Grammatical Error Correction Using Contrastive Learning 21

Dynamic Negative Example Construction for Grammatical Error ...

引用

21st China National Conference on Computational Linguistics, CCL 2022

作者： He, Junyi Zhuang, Junbin Li, Xia Guangzhou Key Laboratory of Multilingual Intelligent Processing School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou China

ISBN: (纸本)9783031183140

Grammatical error correction (GEC) aims at correcting texts with different types of grammatical errors into natural and correct forms. Due to the difference of error type distribution and error density, current grammatical error correction systems may over-correct writings and produce a low precision. To address this issue, in this paper, we propose a dynamic negative example construction method for grammatical error correction using contrastive learning. The proposed method can construct sufficient negative examples with diverse grammatical errors, and can be dynamically used during model training. The constructed negative examples are beneficial for the GEC model to correct sentences precisely and suppress the model from over-correction. Experimental results show that our proposed method enhances model precision, proving the effectiveness of our method. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

A comparative study of four nonlinear dynamic methods and their applications in classification of ship-radiated noise

引用

Defence technology（防务技术） 2022年第2期18卷 183-193页

作者： Yu-xing Li Shang-bin Jiao Bo Geng Qing Zhang You-min Zhang School of Automation and Information Engineering Xi’an University of TechnologyXi’an710048China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of TechnologyXi’an710048China Department of Mechanical Industrial and Aerospace EngineeringConcordia UniversityMontrealQuebec H3G 1M8Canada

Refined composite multi-scale dispersion entropy(RCMDE),as a new and effective nonlinear dynamic method,has been applied in the field of medical diagnosis and fault *** this paper,we first introduce RCMDE into the field of underwater acoustic signal processing for complexity feature extraction of ship radiated noise,and then propose a novel classification method for ship-radiated noise based on RCMDE and k-nearest neighbor(KNN),termed *** results of a comparative experiment show that the proposed RCMDE-KNN classification method can effectively extract the complexity features of ship-radiated noise,and has better classification performance under one and two scales than the other three classification methods based on multi-scale permutation entropy(MPE)and KNN,multi-scale weighted-permutation entropy(MW-PE)and KNN,and multi-scale dispersion entropy(MDE)and KNN,termed MPE-KNN,MW-PE-KNN,and *** is proved that the RCMDE-KNN classification method for ship-radiated noise is feasible and effective,and can obtain a very high recognition rate.

关键词： Nonlinear dynamic Refined composite multi-scale dispersion entropy(RCMDE) Multi-scale dispersion entropy(MDE) Multi-scale weighted-permutation entropy (MW-PE) Multi-scale permutation entropy(MPE) Classification of ship-radiated noise

来源：评论

学校读者我要写书评

暂无评论

Hand Gesture Recognition Method based on mmWave Radar with MobileViT and Knowledge Distillation 16

Hand Gesture Recognition Method based on mmWave Radar with M...

引用

16th International Conference on Signal processing systems, ICSPS 2024

作者： Zhang, Xiangqun Ge, Zhizhou Lu, Kai Du, Genyuan Shen, Jiawen Gao, Xiangqian School of Information Engineering Xuchang University Xuchang461000 China Henan International Joint Laboratory of Polarization Sensing and Intelligent Signal Processing Xuchang461000 China Henan Shengshi Hengxin Technology Co. Ltd Xuchang461111 China

ISBN: (纸本)9781510689251

Human-hand gesture recognition using millimetre wave radar is attractive in human-computer interfaces, industrial Internet of Things, and smart home. However, the existing CNN or RNN model is so complex and large that it is hard to apply to mobile vision tasks and embedded devices. This paper proposes dual lightweight convolutional neural networks, MobileViT and knowledge distillation, to solve this problem. Firstly, we acquire the original radar echoes of frequency-modulated continuous wave (FWCW) signal and reshape the three-dimensional matrix by Chirps * Samples * Frames. Then, we perform the signal processing method to eliminate the noise and static background. Secondly, we employ the Fast Fourier Transform to extract the hand gestures feature map of distance and Doppler information. Finally, the feature map is input into the modified MobileViT to recognize dynamic hand gestures, and knowledge distillation models is used to simplify the model structure. The experimental results show that the parameter space complexity of the constructed model is reduced to 0.018 M, and the computational complexity is 0.082 GFLOPs after knowledge distillation *** method is verified in 12 complex gesture. It has the potential to be applied in mobile tasks and embedded devices. © 2025 SPIE.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Federated Learning based on Feature Transfer: Multi-center Nuclear Segmentation of Histological Images 5

Federated Learning based on Feature Transfer: Multi-center N...

引用

5th International Conference on Frontiers technology of information and Computer, ICFTIC 2023

作者： Lu, Senliang Feng, Bao Chen, Yehang Huang, Zijun School of Electronic Engineering and Automation Guilin University of Electronic Technology Guilin541004 China Laboratory of Intelligent Detection and Information Processing Guilin University of Aerospace Technology Guilin City Guangxi Province541004 China

ISBN: (纸本)9798350309034

Federated learning has enabled multiple medical data centers to collaboratively train segmentation models without sharing data. However, the existence of Non-IID data across different data centers leads to poor model generalization. To address this issue, we propose a personalized federated learning approach based on feature transfer, suitable for multi-center medical image segmentation tasks. Firstly, to construct personalized local segmentation models and reduce the influence of heterogeneous feature information in the global segmentation model, we employ a meta-network to automatically identify and select transferable features from the encoding layers of U-Net. It generates feature transfer weights and constructs a feature transfer loss to enhance the local models' attention to informative features. Secondly, to filter out heterogeneous feature information from each local model and enable the global model to identify and transfer robust features from local models, the meta-network computes feature transfer weights based on the representations of each local model and construct an aggregation loss. This loss is then used to update the feature transfer weights based on the variation of soft dice loss of the global segmentation model. Experimental evaluations are conducted on six central datasets for cell nuclei segmentation tasks, and comparisons are made with three existing federated learning algorithms. The experimental results demonstrate that the proposed method achieves the highest dice coefficient in centers A, B, C, E, and F, with a nearly 10% improvement in the dice coefficient for center F. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral image fusion via weighted nuclear norm regularized sparse matrix factorization 8

Hyperspectral image fusion via weighted nuclear norm regular...

引用

8th International Conference on Electronic technology and information Science, ICETIS 2023

作者： Lu, Jingjing Ma, Mingxi College of Science Nanchang Institute of Technology Jiangxi Nanchang330099 China Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang Institute of Technology Jiangxi Nanchang330099 China

ISBN: (纸本)9781510666535

The fusion of a low spatial resolution hyperspectral image (LR-HSI) and a high spatial resolution multispectral image (HR-MSI) in the same scene is a common method to get a high spatial resolution hyperspectral image (HR-HSI). For the drawback that the standard nuclear norm regularization treats each singular value equally, this paper proposes a weighted nuclear norm model based on sparse matrix factorization (called WNNS) for hyperspectral image fusion. Specifically, we promote the sparsity of fused images by adding the 1 norm of coefficients. Furthermore, to preserve important data components, we combine with the weighted nuclear norm regularization, where different weights are given to singular values. To efficiently solve the proposed model, we apply an alternating direction method of multipliers (ADMM). Experiments show that the proposed method has better performances in terms of numerical results and visual effects. © 2023 SPIE.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

Verifiable searchable symmetric encryption for conjunctive keyword queries in cloud storage

引用

Frontiers of Computer Science 2022年第6期16卷 103-121页

作者： Qingqing GAN Joseph K.LIU Xiaoming WANG Xingliang YUAN Shi-Feng SUN Daxin HUANG Cong ZUO Jianfeng WANG Guangzhou Key Laboratory of Multilingual Intelligent Processing School of Information Science and Technology/School of Cyber SecurityGuangdong University of Foreign StudiesGuangzhou510006China Department of Computer Science Jinan UniversityGuangzhou510632China Faculty of Information Technology Monash UniversityClayton3168Australia State Key Laboratory of Integrated Service Networks(ISN) Xidian UniversityXi’an710071China

Searchable symmetric encryption(SSE)has been introduced for secure outsourcing the encrypted database to cloud storage,while maintaining searchable *** various SSE schemes,most of them assume the server is honest but curious,while the server may be trustless in the real *** a malicious server not honestly performing the queries,verifiable SSE(VSSE)schemes are constructed to ensure the verifiability of the search ***,existing VSSE constructions only focus on single-keyword search or incur heavy computational cost during *** address this challenge,we present an efficient VSSE scheme,built on OXT protocol(Cash et al.,CRYPTO 2013),for conjunctive keyword queries with sublinear search *** proposed VSSE scheme is based on a privacy-preserving hash-based accumulator,by leveraging a well-established cryptographic primitive,Symmetric Hidden Vector Encryption(SHVE).Our VSSE scheme enables both correctness and completeness verifiability for the result without pairing operations,thus greatly reducing the computational cost in the verification ***,the proposed VSSE scheme can still provide a proof when the search result is ***,the security analysis and experimental evaluation are given to demonstrate the security and practicality of the proposed scheme.

关键词： searchable symmetric encryption verifiability conjunctive keyword queries hash-based accumulator cloud storage

来源：评论

学校读者我要写书评

暂无评论

A Genuine-Equilibrium Monte Carlo Sampling-Based Effective Algorithm for Fully-Connected Ising Models

A Genuine-Equilibrium Monte Carlo Sampling-Based Effective A...

引用

2023 IEEE International Conference on Integrated Circuits, Technologies and Applications, ICTA 2023

作者： Wang, Xiangrui Jiang, Dong Zhang, Yang Kang, Hongyuan Yao, Enyi School of Microelectronics South China University of Technology Guangzhou511442 China Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Guangzhou510006 China

ISBN: (纸本)9798350344288

Ising machines have emerged as a potential technique for hardware acceleration in solving combinatorial optimization problems. However, an effective and hardware-implementation-friendly algorithm is still required to further enhance the fully-connected Ising machine's performance. Parallel momentum-tempering (PMT) algorithm is proposed in this paper, incorporating the full parallel updating capability of momentum annealing (MA) with the global exploration in the solution space provided by parallel tempering (PT). PMT exhibits an excellent performance, and a PMT with 8 replicas surpasses MA on the WK2000 max-cut benchmark, achieving a considerable 80%(1k/6k) reduction in required iteration steps while obtaining a mean cut value of 33,160. Besides, PMT is well-matched for hardware implementation versus MA, benefiting from invariant parameters in each replica. © 2023 IEEE.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

A Chinese Sentiment Analysis Model Incorporating Knowledge Graph and Deep Learning 7

A Chinese Sentiment Analysis Model Incorporating Knowledge G...

引用

7th International Conference on Electrical, Mechanical and Computer Engineering, ICEMCE 2023

作者： Zhao, Shengping Chen, Jinlong Qin, Xingguo School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guangxi Guilin541004 China

ISBN: (纸本)9798350382877

With the rapid growth of social media and e-commerce, users are generating large amounts of textual review data on these platforms. Analyzing and mining these comment data is important for governments, enterprises, and consumers to make decisions. Therefore, sentiment analysis, especially for Chinese comments, has become an area of wide interest in industry and academia. Aiming at the characteristics of Chinese online reviews, this paper applies the techniques of knowledge graph and deep learning around sentence-level sentiment analysis and designs a sentiment analysis model that integrates different information such as sentiment knowledge graph and serialized annotation in a deep learning model to improve the accuracy and effectiveness of sentiment analysis of Chinese online reviews. This is important for improving products and services, understanding user needs, and making more informed business and policy decisions. © 2023 IEEE.

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：