检索结果-内蒙古大学图书馆

Neural Networks, Information and Communication Engineering (NNICE), International Conference on

作者： Yudong Zheng Jun Lu College of Computer Science and Technology Heilongjiang University Harbin China College of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

With the prevalence of deep learning, people use multi-modality information for interpretation and reasoning. In this paper, a cross-modality encoder CMEEA (cross-modality encoder representation based on external attention mechanism) is adopted to improve the accuracy of the model. The two external storage units of CMEEA can be regarded as a dictionary of the whole dataset to improve the performance of the network, while learning more representative features of the input and reducing the computational cost. This paper uses five pretraining tasks that help the model learn internal modal and cross-modal relationships. It also verifies the generalizability of the model by applying the pretraining cross-modal model to the visual inference task NLVR 2 , and improves the previous results by 0.1%. By fine-tuning the pretrain parameters, the model improves by 1.3% on visual question answering (VQA).

关键词： Training Deep learning Analytical models Visualization Dictionaries Computational modeling Question answering (information retrieval)

来源：评论

学校读者我要写书评

暂无评论

H-cluster: A novel efficient algorithm for data clustering in sensor networks

引用

Journal of Communications 2011年第2期6卷 168-178页

作者： Guo, Longjiang Ren, Meirui Li, Jinbao Liu, Yong Ai, Chunyu School of Computer Science and Technology Heilongjiang University Harbin 150080 China Key Laboratory of Database and Parallel Computing Heilongjiang Province Harbin 150080 China Computer Science Troy University Troy AL 36082 United States

This paper focuses on the problem of data clustering in wireless sensor networks (WSNs). The data time window is a landmark window, from the time WSN starts working up to the current time. The objective is to group sensory data generated by sensor nodes deployed in a two-dimensional physical space by the similarity of sensory data in the multi-dimensional sensory data space. To perform in-network data clustering efficiently, we propose HilbertMap, a novel dimensionality reduction technique based on the Hilbert Curves, to map a multi-dimensional data space to a two-dimensional physical space. Through this mapping, the communications for clustering mostly occur between geographically nearby sensor nodes. We have conducted simulation experiments on both real-world and synthetic datasets. Our results show that HilbertMap improves the communication efficiency while maintaining a good clustering quality. © 2011 ACADEMY PUBLISHER.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Research on max ordinal in universal combinatorics coding based on GPU parallel computing

Research on max ordinal in universal combinatorics coding ba...

引用

International Conference on Measurement, Information and Control (MIC)

作者： Zhuo Zhang Jun Lu Ting Ting Gao Juan Mo Yu Liu Key Laboratory of Database and Parallel Computing Heilongjiang Province KLDPC HLJU College of CS HLJU Harbin China College of Computer Science and Technology Heilongiiang University

The parallel computing method of max ordinal number in universal combinatorics coding based on GPU is advanced in this paper. The core of universal combinatorics coding computing is ordinal number computing while the calculation of ordinal number depends on the value of max ordinal number. The calculation of max ordinal number is divided into two parts, multiplication and division of large numbers. This paper focus on the GPU parallel computing of the multiplication in max ordinal number calculation, the calculation speed of the multiplication part is increased substantially, and thus improves the efficiency of max ordinal number calculation.

关键词： Graphics processing units parallel processing Artificial intelligence Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

FasterBERT with Double Loss Function Based on Batch Data Preprocessing

FasterBERT with Double Loss Function Based on Batch Data Pre...

引用

International Conference on Electronics, Communications and Information Technology (CECIT)

作者： Pengqi Duan Yudong Zheng Jun Lu College of Computer Science and Technology Heilongjiang University Heilongjiang University HLJU Harbin China Key Laboratory of Database and Parallel Computing of Heilongjiang Province College of Computer Science and Technology Heilongjiang University Heilongjiang University HLJU Harbin China

ISBN: (纸本)9781665437585

Even though pre-trained language models like BERT and XLNet have produced significant consequences on a variety of tasks of natural language processing, they are difficult to deploy in practical applications due to their large number of parameters, and huge calculation and memory costs. In order to improve the training speed and inference speed of the pre-trained model, the FasterBERT model is proposed in this paper. This model combines batch data preprocessing method with knowledge distillation. It increases the model to increase the model speed and maintains the original accuracy. Furthermore, double loss function is incorporated during the knowledge distillation process in this paper, so that the model can better learn the knowledge of the teacher model and the knowledge of the real labels. The accuracy of the model is improved. The effectiveness of the FasterBERT model is demonstrated on 12 datasets in this paper. Training speed of the FasterBERT is 1.1-2.2 times higher than FastBERT and 2-43 times higher than BERT. In addition, the accuracy is up to 0.6% higher than that of FastBERT, and the accuracy is better than that of the BERT model on three datasets. The experiments show that the FasterBERT model proposed in this paper performs well on six Chinese datasets and six English datasets. The speed is greatly improved while the accuracy of the task also has a significant effect.

关键词： Training Costs Bit error rate Data preprocessing Data models Natural language processing Information and communication technology

来源：评论

学校读者我要写书评

暂无评论

DMSA: DYNAMIC MULTI-SCALE UNSUPERVISED SEMANTIC SEGMENTATION BASED ON ADAPTIVE AFFINITY

arXiv

引用

arXiv 2023年

作者： Yang, Kun Lu, Jun College of Computer Science and Technology Heilongjiang University 150080 Harbin China Jiaxiang Industrial Technology Research Institute of HLJU Jining Shandong Province China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

The proposed method in this paper proposes an end-to-end unsupervised semantic segmentation architecture DMSA based on four loss functions. The framework uses Atrous Spatial Pyramid Pooling (ASPP) module to enhance feature extraction. At the same time, a dynamic dilation strategy is designed to better capture multi-scale context information. Secondly, a Pixel-Adaptive Refinement (PAR) module is introduced, which can adaptively refine the initial pseudo labels after feature fusion to obtain high quality pseudo labels. Experiments show that the proposed DSMA framework is superior to the existing methods on the saliency dataset. On the COCO 80 dataset, the MIoU is improved by 2.0, and the accuracy is improved by 5.39. On the Pascal VOC 2012 Augmented dataset, the MIoU is improved by 4.9, and the accuracy is improved by 3.4. In addition, the convergence speed of the model is also greatly improved after the introduction of the PAR module. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A probabilistic group reverse k-nearest-neighbor query in sensor networks 1

引用

7th China Conference of Wireless Sensor Networks, CWSN 2013

作者： Zhu, Jinghua Kan, Bin Liu, Yong Wang, Tong Pan, Liqiang Liu, Dan School of Computer Science and Technology Heilongjiang University Harbin 150080 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin 150080 China College of Information and Communication Engineering Harbin Engineering University Harbin 150001 China School of Computer and Science Technology Harbin School of Technology Harbin 150001 China School of Computer Science Northeast Forestry University Harbin 150001 China

ISBN: (数字)9783642541742

ISBN: (纸本)9783642541735

Group Reverse k-Nearest-Neighbor Query (GRkNN) can be used to evaluate the influences of query objects and has wide applications. Traditional algorithms are not able to obtain satisfied results for uncertain sensor network data. A probabilistic threshold group reverse k nearest neighbor query (PT-GRkNN) is proposed in this paper. PT-GRkNN exploits filter-refine framework, geometric filter and probability filter are proposed to shrink the search space, the final query results can be obtained by refine phase. Experimental results show that the efficiency of PT-GRkNN is better than the existing methods. © 2014 Springer-Verlag Berlin Heidelberg.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

DMSA: Dynamic Multi-Scale Unsupervised Semantic Segmentation Based On Adaptive Affinity

DMSA: Dynamic Multi-Scale Unsupervised Semantic Segmentation...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kun Yang Jun Lu College of Computer Science and Technology Heilongjiang University Harbin China Jiaxiang Industrial Technology Research Institute of HLJU Jining China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

关键词： Training Representation learning Adaptation models Semantic segmentation Semantics Signal processing Transformers

来源：评论

学校读者我要写书评

暂无评论

Design of Radio-over-Fiber Distributed Antenna System and Application of Wireless Positioning

Design of Radio-over-Fiber Distributed Antenna System and Ap...

引用

IEEE Information Technology, Networking, Electronic and Automation Control Conference

作者： Hao Yun Wei Ji Rui Yin Key Laboratory of Database and Parallel Computing of Heilongjiang Province Laboratory of Intelligent Communications and Multimedia Information Processing ShanDong University Qingdao China School of Information Science and Engineering ShanDong University Qingdao China

ISBN: (数字)9781728143903

ISBN: (纸本)9781728143910

In this paper, a radio-over-fiber distributed antenna system (ROF-DAS) and application of wireless positioning are proposed. The modified Medium Access Control (MAC) frame, optical switch array, ROF network based on star topology and Reflective Semiconductor Optical Amplifier (RSOA) are employed to design the system. Based on the structure, wireless positioning could be achieved by Time Division Multiplexing-Time Difference of Arrival (TDM-TDOA) technology combined with Chan assisted Taylor algorithm. The quality of signal transmission is evaluated by Q Factor, and the positioning accuracy is performed in terms of the antennas amount using the positioning algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NKMH: A Neural Efficient Recommendation Based on Neighborhood key Information Aggregation of Modified Hawkes

NKMH: A Neural Efficient Recommendation Based on Neighborhoo...

引用

IEEE Annual International Computer Software and Applications Conference (COMPSAC)

作者： Xin Xu Nan Wang Hu Jin Yang Liu Kun Li Key Laboratory of Database and Parallel Computing of Heilongjiang Province School of Computer Science and Technology Heilongjiang University Harbin China Postdoctoral Program of Heilongjiang Hengxun Technology Co. Ltd School of Computer Science and Technology Heilongjiang University Harbin China

ISBN: (数字)9781665488105

ISBN: (纸本)9781665488112

The rapid development of neural networks has con-tributed to the increasing maturity of recommendation systems. However, deep neural networks have poor interpretability for models and do not show strong advantages for sparse data and noisy data. Recently, Hawkes process has become more and more focused for its good interpretability with probabilistic models. Based on this, we proposes A Neural Efficient Recommendation Model Based on Neighborhood key Information Aggregation of Modified Hawkes(NKMH). The model utilizes a neural network and designs three modules to jointly fit the modified Hawkes process. It not only inherits the high interpretability of Hawkes, but also effectively solves the problem of poor prediction ability of the Hawkes process. Besides, we present a novel key information search strategy(KISS), which can effectively remove the noise in a session and alleviate the sparsity of the data to some extent. Extensive experiments on two datasets show that the NKMH model outperforms many current popular models.

关键词： Deep learning Conferences Neural networks Predictive models Search problems Probabilistic logic Software

来源：评论

学校读者我要写书评

暂无评论

Faster BERT with Double Loss Function Based on Batch Data Preprocessing

Faster BERT with Double Loss Function Based on Batch Data Pr...

引用

作者： Pengqi Duan Yudong Zheng Jun Lu College of Computer Science and Technology Heilongiiang University Heilongjiang UniversityHLJU College of Computer Science and Technology Heilongjiang University Heilongjiang UniversityHLJU College of Computer Science and Technology Heilongiiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province Heilongjiang University Heilongjiang UniversityHLJU

Even though pre-trained language models like BERT and XLNet have produced significant consequences on a variety of tasks of natural language processing,they are difficult to deploy in practical applications due to their large number of parameters,and huge calculation and memory *** order to improve the training speed and inference speed of the pretrained model,the FasterBERT model is proposed in this *** model combines batch data preprocessing method with knowledge *** increases the model to increase the model speed and maintains the original ***,double loss function is incorporated during the knowledge distillation process in this paper,so that the model can better learn the knowledge of the teacher model and the knowledge of the real *** accuracy of the model is *** effectiveness of the FasterBERT model is demonstrated on 12 datasets in this *** speed of the FasterBERT is 1.1-2.2 times higher than FastBERT and 2-43 times higher than *** addition,the accuracy is up to 0.6% higher than that of FastBERT,and the accuracy is better than that of the BERT model on three *** experiments show that the FasterBERT model proposed in this paper performs well on six Chinese datasets and six English *** speed is greatly improved while the accuracy of the task also has a significant effect.

关键词： pre-trained language model FasterBert model double loss function batch data processing knowledge distillation

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：