检索结果-内蒙古大学图书馆

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Ni, Guangsen Zhang, Hongguang Zhao, Jing Xu, Liyang Yang, Wenjing Lan, Long Institute for Quantum Information and State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology Changsha410073 China Systems Engineering Institute AMS Beijing China

ISBN: (纸本)9783030893699

How to learn concepts from few-shot samples remains an open challenge in the deep learning era. The previous meta-learning methods require a large number of annotated samples in the training phase, which still contributes to high manual-labeling costs. In this paper, we propose a unsupervised few-shot learning framework and pointed out that negative queue constructed via randomly sampling contains many false-negative samples (noise), which has negative impacts on the model’s generalized performance especially when only few samples are available. Specially, we propose an Attention-based Noise Filtering (ANF) strategy to make momentum contrastive loss more applicable to few-shot learning scenario. In addition, we also propose a dynamic momentum update method, which can greatly improve the classification accuracy. Our evaluations demonstrate state-of-the-art unsupervised few-shot learning performance, which is comparable to supervised baseline models. © 2021, Springer Nature Switzerland AG.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Symbolic Execution of MPI Programs with One-Sided Communications

Symbolic Execution of MPI Programs with One-Sided Communicat...

引用

Asia-Pacific Conference on Software Engineering

作者： Nenghui Hu Zheng Bian Ziqi Shuai Zhenbang Chen Yufeng Zhang College of Computer National University of Defense Technology China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology China State Key Laboratory of High Performance Computing National University of Defense Technology China College of Computer Science and Electronic Engineering Hunan University Changsha China

Message-passing interface (MPI) programs are non-deterministic and challenging to ensure correctness. The introduction of one-sided communications makes the problem of non-determinism more severe for MPI programs. This paper reports our in-progress work of symbolic execution for the MPI programs with one-sided communications. Our approach can cover the non-determinism caused by the inputs, one-sided communication, and message- passing operations of MPI programs. The preliminary evaluation's results indicate the promising of our approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Short- and Long-Term Mask Representation for Multivariate Time Series Anomaly Detection

arXiv

引用

arXiv 2022年

作者： Miao, Qiucheng Xu, Chuanfu Zhan, Jun Zhu, Dong Wu, Chengkun Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Hunan Changsha China

Anomaly detection of multivariate time series is meaningful for system behavior monitoring. This paper proposes an anomaly detection method based on unsupervised Short- and Long-term Mask Representation learning(SLMR). The main idea is to extract short-term local dependency patterns and long-term global trend patterns by using multi-scale residual dilated convolution and Gated Recurrent Unit(GRU) respectively. Furthermore, our approach can comprehend temporal contexts and feature correlations by combining spatial-temporal masked self-supervised representation learning and sequence split. It considers the importance of features is different, and we introduce the attention mechanism to adjust the contribution of each feature. Finally, a forecasting-based model and a reconstruction-based model are integrated to focus on single timestamp prediction and latent representation of time series. Experiments show that the performance of our method outperforms other state-of-the-art models on three real-world datasets. Further analysis shows that our method is good at anomaly localization. © 2022, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

high ORDER FINITE DIFFERENCE/SPECTRAL METHODS TO A WATER WAVE MODEL WITH NONLOCAL VISCOSITY

引用

Journal of Computational Mathematics 2020年第4期38卷 580-605页

作者： Mohammad Tanzil Hasan Chuanju Xu School of Mathematical Sciences and Fujian Provincial Key Laboratory of Mathematical Modeling and High Performance Scientific Computing Xiamen UniversityXiamen 361005China

In this paper,efficient numerical scheme is proposed for solving the water wave model with nonlocal viscous term that describe the propagation of surface water *** using the Caputo fractional derivative definition to approximate the nonlocal fractional operator,finite difference method in time and spectral method in space are constructed for the considered *** proposed method employs known 5/2 order scheme for fractional derivative and a mixed linearization for the nonlinear *** analysis shows that the proposed numerical scheme is unconditionally stable and error estimates are provided to predict that the second order backward differentiation plus 5/2 order scheme converges with order 2 in time,and spectral accuracy in *** numerical results are provided to verify the efficiency and accuracy of our theoretical ***,the decay rate of solutions are investigated.

关键词： Water waves Nonlocal viscosity Finite difference Spectral method Conver-gence order Decay rate

来源：评论

学校读者我要写书评

暂无评论

Unsatisfiable Core Based Constraint Solving Cache in Symbolic Execution

Unsatisfiable Core Based Constraint Solving Cache in Symboli...

引用

Asia-Pacific Conference on Software Engineering

作者： Ziqi Shuai Zhenbang Chen Yufeng Zhang Hengbiao Yu Ji Wang College of Computer National University of Defense Technology China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology China State Key Laboratory of High Performance Computing National University of Defense Technology China College of Computer Science and Electronic Engineering Hunan University Changsha China

Constraint solving stands out as a significant bot-tleneck in symbolic execution. Caching is a commonly adopted approach to alleviate this bottleneck. However, the cutting-edge caching technique targeting unsatisfiable constraints, known as unsatisfiable core caching, primarily involves checking whether the constraint being solved contains an unsatisfiable core that has been previously collected. Such straightforward reuse frequently proves less effective in numerous scenarios. In this paper, we present a novel method to enhance the utilization of unsatisfiable cores. By excavating unsatisfiable cores, our method can compute an easily solvable over-approximation that tends to be unsatis-fiable for each constraint, which facilitates the determination of the satisfiability of the original constraint. We implemented our method on KLEE symbolic executor. The evaluation results on 27 real-world programs are encouraging.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Node Sorting Method for K2 Algorithm in Bayesian Network Structure Learning

A Node Sorting Method for K2 Algorithm in Bayesian Network S...

引用

2020 IEEE International Conference on Artificial Intelligence and Computer Applications, ICAICA 2020

作者： Gao, Fan Huang, Da State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China

ISBN: (纸本)9781728170046

Bayesian network is an important model for reasoning in an uncertain environment. A reliable node rank is required by K2 algorithm to learn Bayesian network structure better. To provide a high-quality node rank tailored for K2 algorithm, we propose a node priority-based sorting algorithm. Given observable data only, our algorithm can be employed to learn a node rank without expert knowledge. Specifically, MCMC algorithm is first utilized to yield some Bayesian network structures that can sufficiently fit the observed data. We then define the priority of each node in these network structures. Node rank is finally obtained through weighted scoring based on the priority. The empirical results show that our sorting algorithm performs significantly better than commonly used methods, e.g., randomly sorting and MCMC algorithm, on an Asia network-learning dataset. © 2020 IEEE.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Algorithm of Quantum-Behaved Particle Swarm Optimization and Adam for ANN Training and Application for Classification Prediction

A Hybrid Algorithm of Quantum-Behaved Particle Swarm Optimiz...

引用

New Trends in Computational Intelligence (NTCI), International Conference on

作者： Hanqiu Ye Jianping Dong School of Mathematics Nanjing University of Aeronautics and Astronautics Nanjing China key Laboratory of Mathematical Modelling and High Performance Computing of Air Vehicles (NUAA) MIIT Nanjing China

The study of neural networks has become increasingly popular as artificial intelligence has advanced. In addition to several new types of networks and their applications in various fields, neural network optimization has also drawn a lot of attention. Traditional techniques for optimizing the parameters of neural networks are gradient descent algorithms. The drawback of gradient descent algorithms is that they may easily fall into local optima because of the characteristics of local optimization. Meanwhile, several meta-heuristic algorithms have been attempted to optimize neural networks, but the performance is also limited due to insufficient fine search capability. This work proposes the hybrid algorithm HAQPSO to improve the draw-back of gradient descent algorithms, which not only combines Adam with the Quantum-behaved Particle Swarm Optimization (QPSO) but also introduces the hybrid strategy to facilitate information transfer between the algorithms and enhances the efficiency. The proposed algorithm was tested on the Iris dataset and compared with classical gradient descent algorithms and Particle Swarm Optimization (PSO). The experimental results prove that HAQPSO can improve the searching capability while enhancing stability and achieving fast convergence, which is a competitive algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning with noise: Improving distantly-supervised fine-grained entity typing via automatic relabeling 29

Learning with noise: Improving distantly-supervised fine-gra...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Zhang, Haoyu Long, Dingkun Xu, Guangwei Zhu, Muhua Xie, Pengjun Huang, Fei Wang, Ji State Key Laboratory of High Performance Computing National University of Defense Technology Alibaba Group

ISBN: (纸本)9780999241165

Fine-grained entity typing (FET) is a fundamental task for various entity-leveraging applications. Although great success has been made, existing systems still have challenges in handling noisy samples in training data introduced by distant supervision method. To address these noises, previous studies either focus on processing the clean samples (i.e., have only one label) and noisy samples (i.e., have multiple labels) with different strategies or filtering the noisy labels based on the assumption that the distantly-supervised label set certainly contains the correct type label. In this paper, we propose a probabilistic automatic relabeling method which treats all training samples uniformly. Our method aims to estimate the pseudo-truth label distribution of each sample, and the pseudo-truth distribution will be treated as part of trainable parameters which are jointly updated during the training process. The proposed approach does not rely on any prerequisite or extra supervision, making it effective on real applications. Experiments on several benchmarks show that our method outperforms previous competitive approaches and indeed alleviates the noisy labeling problem. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling Neural Networks Training Process with Markov Decision Process 2

Modeling Neural Networks Training Process with Markov Decisi...

引用

2nd International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2021

作者： Bai, Yantao Liu, Wanwei Mao, Xinjun Liang, Zhen National University of Defense Technology Key Laboratory of Software Engineering for Complex Systems Changsha China College of Computer Science National University of Defense Technology Changsha China Institute for Quantum Information National University of Defense Technology State Key Laboratory of High Performance Computing Changsha China

ISBN: (纸本)9781665421867

With the development of computer technology, statistics-based machine learning method has made great break-throughs, and also improved the development of artificial intelligence. Nevertheless, as a very influential model, neural networks are still treated as 'black boxes'. The results of neural networks are extremely sensitive to the training samples, which lead to great challenges to the controllability of the algorithm. With the wide application of machine learning, demand for interpretability and controllability of neural networks algorithms is increasing. As a result, various scholars have tried to explain and verify neural networks algorithms based on formal methods in recent years. In this paper, a method (called MNNTP) is presented to model the training process of neural networks by using a Markov decision process (MDP). Through MNNTP, the neural networks are abstracted into the form of MDP, which makes notable contributions for verifying some mathematical properties of the neural networks. © 2021 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

ParallelDualSPHysics: supporting efficient parallel fluid simulations through MPI-enabled SPH method 22

ParallelDualSPHysics: supporting efficient parallel fluid si...

引用

Proceedings of the 51st International Conference on Parallel Processing

作者： Sifan Long Xiao-Wei Guo Xiaokang Fan Chao Li Kelvin Wong Ran Zhao Yi Liu Sen Zhang Canqun Yang College of Computer National University of Defense Technology China Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology China College of Computer Central South University China

ISBN: (纸本)9781450397339

Smoothed Particle Hydrodynamics (SPH) is a classical mesh-free particle method which has been successfully applied in the field of Computational Fluid Dynamics (CFD). Its advantages over traditional mesh-based methods have made it very popular in simulating problems involving large deformation and free-surface flow. The high computational cost of the SPH method has obstructed its vast application. A lot of research effort has been devoted to accelerating the SPH method using GPU and multi threading. However, developing efficient parallel SPH algorithms on modern high-performance computers (HPCs) remains significantly challenging, especially for simulating real-world engineering problems involving hundreds of millions of particles. In this paper, we proposed an MPI-enabled parallel SPH algorithm and developed the ParallelDualSPHysics1, an open-source software supporting efficient parallel fluid simulations. Based on an efficient domain decomposition scheme, the essential data structure and algorithms of DualSPHysics were refactored to build the parallel version. For collaborating with evenly distributed particles on a distributed-memory HPC system, the parallel particle interaction and particle update modules were introduced, which enabled the SPH solver to synchronize computations among multiple processors using MPI. In addition, the redesigned pre-processing and post-processing capabilities of the ParallelDualSPHysics supported the applications of this software in a wide range of areas. Real-life test cases with up to 120 million particles were simulated and analyzed on a modern HPC system. The results showed that the parallel efficiency of ParallelDualSPHysics exceeds 90 with up to 1024 CPU cores. It indicated that ParallelDualSPHysics has the potential for large-scale engineering applications.

关键词： Computational Fluid Dynamics Smoothed Particle Hydrodynamics ParallelDualSPHysics Parallel computing

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：