检索结果-内蒙古大学图书馆

Transfer learning for deep neural network-based partial differential equations solving

Advances in Aerodynamics 2021年第1期3卷 635-648页

作者： Xinhai Chen Chunye Gong Qian Wan Liang Deng Yunbo Wan Yang Liu Bo Chen Jie Liu Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense TechnologyChangshaChina China Aerodynamics Research and Development Center MianyangChina.

Deep neural networks(DNNs)have recently shown great potential in solving partial differential equations(PDEs).The success of neural network-based surrogate models is attributed to their ability to learn a rich set of solution-related ***,learning DNNs usually involves tedious training iterations to converge and requires a very large number of training data,which hinders the application of these models to complex physical *** address this problem,we propose to apply the transfer learning approach to DNN-based PDE solving *** our work,we create pairs of transfer experiments on Helmholtz and Navier-Stokes equations by constructing subtasks with different source terms and Reynolds *** also conduct a series of experiments to investigate the degree of generality of the features between different *** results demonstrate that despite differences in underlying PDE systems,the transfer methodology can lead to a significant improvement in the accuracy of the predicted solutions and achieve a maximum performance boost of 97.3%on widely used surrogate models.

关键词： Deep neural network Partial differential equation Surrogate model Transfer learning

来源：评论

学校读者我要写书评

暂无评论

DIPP—An LLC replacement policy for on-chip dynamic heterogeneous multi-core architecture

DIPP—An LLC replacement policy for on-chip dynamic heteroge...

引用

International Conference of Young Computer Scientists, Engineers and Educators, ICYCSEE 2015

作者： Yang, Zhang Zuocheng, Xing Xiao, Ma Science and technology on Parallel and distributed processing laboratory National University of Defense Technology ChangSha China

ISBN: (纸本)9783662462478

As the big data era is coming, it brings new challenges to the massive data processing. A combination of GPU and CPU on chip is the trend to release the pressure of large scale computing. We found that there are different memory access characteristics between GPU and CPU. The most important one is that the programs of GPU include a large number of threads, which lead to higher access frequency in cache than the CPU programs. Although the LRU policy favors the programs with high memory access frequency, the programs of GPU can’t get the corresponding performance boost even more cache resources are provided. So LRU policy is not suitable for heterogeneous multi-core processor. Based on the different characteristics of GPU and CPU programs on memory access, this paper proposes an LLC dynamic replacement policy--DIPP (Dynamic Insertion/ Promotion Policy) for heterogeneous multi-core processors. The core idea of the replacement policy is to reduce the miss rate of the program and enhance the overall system performance by limiting the cache resources that GPU can acquire and reducing the thread interferences between programs. Experiments compare the DIPP replacement policy with LRU and we conduct a classified discussion according to the program results of GPU. Friendly programs enhance 23.29% on the average performance (using arithmetic mean). Large working sets programs can improve 13.95%, compute-intensive programs enhance 9.66% and stream class programs improve 3.8%. © Springer-Verlag Berlin Heidelberg 2015.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

SMVAR: A Novel RNN Accelerator Based on Non-blocking Data Distribution Structure 25

SMVAR: A Novel RNN Accelerator Based on Non-blocking Data Di...

引用

25th IEEE International Conferences on High Performance Computing and Communications, 9th International Conference on Data science and Systems, 21st IEEE International Conference on Smart City and 9th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Xu, Jinwei Jiang, Jingfei Xu, Shiyao Gao, Lei National University of Defense Technology Science and Technology on Parallel and Distributed Laboratory Hunan Changsha China

ISBN: (纸本)9798350330014

Recurrent neural networks (RNNs) have become common models in the field of artificial intelligence to process temporal sequence task, such as speech recognition, text analysis, natural language processing, etc. To speedup RNNs inference, previous research proposed model sparse pruning techniques. However, the pruning rate of existing sparse pruning algorithms will be affected by pruning granularity and hardware friendliness. In order to approximate nonstructured pruning algorithm, this paper proposes Large Region Balanced Sparse (LRBS) pruning method, which does not limit sub-matrix shape and effectively improves pruning rate. Furthermore, we propose Sparse Matrix Vector Multiplication Accelerator for RNNs (SMVAR), which adopt non-blocking data distribution structure to solve the problem of efficient execution of large region irreg-ular matrix multiplication. To further improve the accelerator performance, SMVAR fine-grained adjusts the pipeline between macro-operations to reduce the idle of compute components. In addition, according to the coarse-grained block characteristics of LRBS algorithm, we develop the coarse-grained parallelism of accelerator with multiply compute units(CUs) structure. Experiments show that the pruning rate of our proposed LRBS is 1.25x-2.5x higher than that of the existing pruning algorithms. Compared with the existing work, the execution efficiency is improved by more than 2.02x-35.9x in the same application scenario. © 2023 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

A Novel Interactive Recurrent Attention Network for Emotion-Cause Pair Extraction 3

A Novel Interactive Recurrent Attention Network for Emotion-...

引用

3rd International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2020

作者： Jia, Xiangyu Chen, Xinhai Wan, Qian Liu, Jie Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha China

ISBN: (纸本)9781450388115

Unlike Emotion Cause Extraction (ECE) task which consists of pre-annotate emotions and passage, emotion-cause pair extraction (ECPE) aims at extracting potential emotions and corresponding causes in the document without the need for pre-annotations. Traditional ECPE solutions divide the extracting emotions and causes operation into two separate parts. However, separating the bidirectional dependence between emotion and cause may lose a lot of potentially useful information. In this paper, we propose a novel interactive recurrent attention network (IRAN). Our approach focuses on the bidirectional impact between emotions and causes, and extracts emotions and causes simultaneously. The information in the document can be fully exploited through multiple modeling and information extraction. Our emotion-specific transformation and distance fusion correlation can adaptively focus on the emotions and the distance, gracefully incorporate them into a distinguishable neural network attention framework. The experimental results show that our proposed model achieves better performance than other widely-used models on the ECPE corpus. © 2020 ACM.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

NVLAN: A Novel VLAN technology for Scalable Multi-tenant Datacenter Networks 2

NVLAN: A Novel VLAN Technology for Scalable Multi-tenant Dat...

引用

2nd International Conference on Advanced Cloud and Big Data, CBD 2014

作者： Hu, Yang Li, Huiba Peng, Yuxing Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Computer Science Department China

ISBN: (纸本)9781479980857

Nowadays, cloud providers of 'Infrastructure as a service' require datacenter networks to support virtualization and multi-tenancy at large scale, while it brings a grand challenge to datacenters. Traditional network technologies of datacenters and common commodity devices of network can not meet these new needs. In this paper, we present NVLAN, a novel VLAN technology for scalable multi-tenant datacenter networks. NVLAN eliminates the quantity limitation of logic isolated networks on VLAN through a slight modification. NVLAN can be applied to very large-scale datacenter networks, without the need of expensive and dedicated switches. Through encapsulation of tenant's packets, NVLAN provides tenants with full address space virtualization to configure their own logic network. We implemented NVLAN on a test bed, and demonstrated that it can be scaled up to large numbers of multi-tenant networks with negligible overhead. © 2014 IEEE.

关键词： Virtualization

来源：评论

学校读者我要写书评

暂无评论

High Performance Interconnect Network for Tianhe System

引用

Journal of Computer science & technology 2015年第2期30卷 259-272页

作者：廖湘科庞征王克非卢宇彤谢旻夏军董德尊所光 College of Computer National University of Defense Technology Changsha 410073 Science and Technology on Parallel and Distributed Processing Laboratory National Changsha 410073 China China University of Defense Technology State Key Laboratory of High Performance Computing National University of Defense Technology Changsha 410073 China

In this paper, we present the Tianhe-2 interconnect network and message passing services. We describe the architecture of the router and network interface chips, and highlight a set of hardware and software features effectively supporting high performance communications, ranging over remote direct memory access, collective optimization, hardwareenable reliable end-to-end communication, user-level message passing services, etc. Measured hardware performance results are also presented.

关键词： Tianhe-2 supercomputer interconnect network router architecture network interface architecture user-level message passing

来源：评论

学校读者我要写书评

暂无评论

Effective Anomaly Detection Based on Reinforcement Learning in Network Traffic Data 27

Effective Anomaly Detection Based on Reinforcement Learning ...

引用

27th IEEE International Conference on parallel and distributed Systems, ICPADS 2021

作者： Wang, Zhongyang Wang, Yijie Xu, Hongzuo Wang, Yongjun National University of Defense Technology Science and Technology on Parallel Distributed Processing Laboratory College of Computer China

ISBN: (纸本)9781665408783

Mixed-type data with both categorical and numerical features are ubiquitous in network security, but the existing methods are minimal to deal with them. Existing methods usually process mixed-type data through feature conversion, whereas their performance is downgraded by information loss and noise caused by the transformation. Meanwhile, existing methods usually superimpose domain knowledge and machine learning in which fixed thresholds are used. It cannot dynamically adjust the anomaly threshold to the actual scenario, resulting in inaccurate anomalies obtained, which results in poor performance. To address these issues, this paper proposes a novel Anomaly Detection method based on Reinforcement Learning, termed ADRL, which uses reinforcement learning to dynamically search for thresholds and accurately obtain anomaly candidate sets, fusing domain knowledge and machine learning fully and promoting each other. Specifically, ADRL uses prior domain knowledge to label known anomalies and uses entropy and deep autoencoder in the categorical and numerical feature spaces, respectively, to obtain anomaly scores combining with known anomaly information, which are integrated to get the overall anomaly scores via a dynamic integration strategy. To obtain accurate anomaly candidate sets, ADRL uses reinforcement learning to search for the best threshold. Detailedly, it initializes the anomaly threshold to get the initial anomaly candidate set and carries on the frequent rule mining to the anomaly candidate set to form the new knowledge. Then, ADRL uses the obtained knowledge to adjust the anomaly score and get the score modification rate. According to the modification rate, different threshold modification strategies are executed, and the best threshold, that is, the threshold under the maximum modification rate, is finally obtained, and the modified anomaly scores are obtained. The scores are used to re-carry out machine learning to improve the algorithm's accuracy for anomalo

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Versionized process based on non-volatile random-access memory for fine-grained fault tolerance

引用

Frontiers of Information technology & Electronic Engineering 2018年第2期19卷 192-205页

作者： Wen-zhe ZHANG Kai LU Xiao-ping WANG Science and Technology on Parallel and Distributed Processing Laboratory College of ComputerNational University of Defense Technology

Non-volatile random-access memory（NVRAM） technology is maturing rapidly and its byte-persistence feature allows the design of new and efficient fault tolerance mechanisms. In this paper we propose the versionized process（Ver P）, a new process model based on NVRAM that is natively non-volatile and fault tolerant. We introduce an intermediate software layer that allows us to run a process directly on NVRAM and to put all the process states into NVRAM, and then propose a mechanism to versionize all the process data. Each piece of the process data is given a special version number, which increases with the modification of that piece of data. The version number can effectively help us trace the modification of any data and recover it to a consistent state after a system *** with traditional checkpoint methods, our work can achieve fine-grained fault tolerance at very little cost.

关键词： Non-volatile memory Byte-persistence Versionized process Version number

来源：评论

学校读者我要写书评

暂无评论

Large-scale parallel exact diagonalization algorithm of the Hubbard model on Tianhe-2 supercomputer 22

Large-scale parallel exact diagonalization algorithm of the ...

引用

6th International Conference on High Performance Compilation, Computing and Communications, HP3C 2022

作者： Li, Biao Liu, Jie Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Hunan Changsha China

ISBN: (纸本)9781450396295

We propose a parallel exact diagonalization method for solving the large-scale Hubbard model. The core of this algorithm is the parallelization of the Lanczos algorithm, for which we propose a hierarchical communication model and a fast strategy for finding nonzero elements of large-scale matrix, starting only from the symmetry of Hamiltonian matrix. The effect of our parallel algorithm was tested on the Tianhe-2 supercomputer, where the strong scaling efficiency could reach 53% for 30,000 cores in a 140-billion dimensional matrix, and the weak scaling efficiency remained above 40% for 60,000 cores in a 730-billion dimensional matrix. © 2022 ACM.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-class contour preserving classification

Multi-class contour preserving classification

引用

13th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2012

作者： Fuangkhon, Piyabute Tanprasert, Thitipong Distributed and Parallel Computing Research Laboratory Faculty of Science and Technology Assumption University Bangkok Thailand

ISBN: (纸本)9783642326387

The original contour preserving classification technique was proposed to improve the robustness and weight fault tolerance of a neural network applied with a two-class linearly separable problem. It was recently found to be improving the level of accuracy of two-class classification. This paper presents an augmentation of the original technique to improve the level of accuracy of multi-class classification by better preservation of the shape or distribution model of a multi-class problem. The test results on six real world multi-class datasets from UCI machine learning repository present that the proposed technique supports multi-class data and can improve the level of accuracy of multi-class classification more effectively. © 2012 Springer-Verlag.

关键词： 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：