检索结果-内蒙古大学图书馆

Clause-level Relationship-aware Math Word Problems Solver

Machine Intelligence Research 2022年第5期19卷 425-438页

作者： Chang-Yang Wu Xin Lin Zhen-Ya Huang Yu Yin Jia-Yu Liu Qi Liu Gang Zhou Anhui Province Key Laboratory of Big Data Analysis and Application School of Data ScienceUniversity of Science and Technology of ChinaHefei 230026China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Laboratory of Mathematical Engineering and Advanced Computing Information Engineering UniversityZhengzhou 450001China

Automatically solving math word problems,which involves comprehension,cognition,and reasoning,is a crucial issue in artificial intelligence *** math word problem solvers mainly work on word-level relationship extraction and the generation of expression solutions while lacking consideration of the clause-level *** this end,inspired by the theory of two levels of process in comprehension,we propose a novel clause-level relationship-aware math solver(CLRSolver)to mimic the process of human comprehension from lower level to higher ***,in the lower-level processes,we split problems into clauses according to their natural division and learn their *** the higher-level processes,following human′s multi-view understanding of clause-level relationships,we first apply a CNN-based module to learn the dependency relationships between clauses from word relevance in a local ***,we propose two novel relationship-aware mechanisms to learn dependency relationships from the clause semantics in a global ***,we enhance the representation of clauses based on the learned clause-level dependency *** expression generation,we develop a tree-based decoder to generate the mathematical *** conduct extensive experiments on two datasets,where the results demonstrate the superiority of our framework.

关键词： Artificial intelligence(AI) artificial neural network(ANN) computational mathematics machine intelligence machine learning

来源：评论

学校读者我要写书评

暂无评论

A Software/Hardware Co-design Local Irregular Sparsity Method for Accelerating CNNs on FPGA 22

A Software/Hardware Co-design Local Irregular Sparsity Metho...

引用

Workshop Proceedings of the 51st International Conference on Parallel Processing

作者： Jiangwei Shang Zhan Zhang Chuanyou Li Kun Zhang Lei Qian Hongwei Liu Harbin Institute of Technology China Southeast University China State Key Laboratory of Mathematical Engineering and Advanced Computing China

ISBN: (纸本)9781450394451

Convolutional neural networks (CNNs) have been widely used in different areas. The success of CNNs comes with a huge amount of parameters and computations, and nowaday CNNs still keep moving toward larger structures. Although larger structures often bring about better inference accuracy, the increasing size also slows the inference speed down. Recently, various parameter sparsity methods have been proposed to accelerate CNNs by reducing the number of parameters and computations. Existing sparsity methods could be classified into two categories: unstructured and structured. Unstructured sparsity methods easily cause irregularity and thus have a suboptimal speedup. On the other hand, the structured sparsity methods could keep regularity by pruning the parameters following a certain pattern but result in low sparsity. In this paper, we propose a software/hardware co-design approach to bring local irregular sparsity into CNNs. Benefiting from the local irregularity, we design a row-wise computing engine, RConv Engine, to achieve workload balance and remarkable speedup. The experimental results show that our software/hardware co-design method can achieve a 10.9x speedup than the state-of-the-art methods with a negligible accuracy loss.

关键词： field-programmable gate arrays (FPGAs) hardware accelerator convolutional neural network software/hardware co-design sparsity method

来源：评论

学校读者我要写书评

暂无评论

A Relation-Oriented Method for Joint Entity and Relation Extraction Based on Neural Network 21

A Relation-Oriented Method for Joint Entity and Relation Ext...

引用

5th International Conference on Electronic Information Technology and Computer engineering, EITCE 2021

作者： Hu, Hongwei Yin, Meijuan Liu, Xiaonan Key Laboratory of Cyberspace Situation Awareness of Henan Zhengzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781450384322

Entity and relation extraction is a basic task of information extraction in natural language processing. At present, Entity and relation extraction based on artificial intelligence has been widely studied, but most methods adopt the idea of identifying the entity first and then extracting the relation, which suffers from the problems of overlapping triple and entity redundancy. We propose a Relation-Oriented method for Joint Entity and Relation Extraction (ROJER), which first extracts the relation types contained in the text through the relation extraction module, then the pre-extracted relation types are integrated into the entity recognition module, reduce the focus on irrelevant entities and avoid extracting redundant entities. Then the entity pairs corresponding to the extracted relation types are identified to tackle the overlapping triple problem and finally extract all the relation triples. Experiments on the DuIE dataset show that the F1 score of ROJER reaches 78.4%, which is 1.2% higher than the CasRel model, confirming the validity of our method. © 2021 ACM.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

VulD-CodeBERT: CodeBERT-Based Vulnerability Detection Model for C/C++ Code

VulD-CodeBERT: CodeBERT-Based Vulnerability Detection Model ...

引用

International Conference on Communications, Information System and Computer engineering (CISCE)

作者： Zhe Xiong Weiyu Dong School of Computer Science and Artificial Intelligence Zhengzhou University Zhengzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Information Engineering University Zhengzhou China

ISBN: (数字)9798350353174

ISBN: (纸本)9798350353181

Recently, deep learning techniques have received widespread attention in code vulnerability and vulnerability detection. However, there are some problems with current vulnerability detection techniques, firstly, because of the non-homogeneity of vulnerability categories and quantities, there are omission false positives and overfitting problems for vulnerabilities with a small amount of data. Second, the existing detection methods have limited ability to characterize the code, there is insufficient depth of characterization, does not contain all of its vulnerability characteristics or is interspersed with useless information. Finally, the current research does not use the powerful feature mining capability of pre-trained models and does not employ model fusion to increase the effectiveness of model vulnerability detection. To solve the above problems, this paper proposes a new deep learning based pre-trained model for code vulnerability detection tool VulD-CodeBERT. By fine-tuning CodeBERT, a code adaptation extension for pre-trained models developed by Microsoft, the CodeBERT model can solve the problem of not being able to learn the vulnerability patterns due to insufficient data, thus resulting in missed false alarms. The sequence output from the CodeBERT model are added to a BiLSTM network with an attention mechanism to mine the local key features of the vulnerabilities combined with the global features of the pooler output from the CodeBERT model to deeply mine the dependencies between the vulnerability statements and derive the probability of the existence of the vulnerability. For vulnerability types that are difficult to uncover captured features or the number of samples is not enough, a polynomial plain Bayesian classifier is used for detection, and finally the two models are combined to deeply mine the vulnerability features, thus solving the problem of difficult and small samples, and reducing the leakage rate and false alarm rate. Experimental results sh

关键词： Deep learning Adaptation models Codes Attention mechanisms Computational modeling Feature extraction Polynomials

来源：评论

学校读者我要写书评

暂无评论

SPAFuzz: Web Security Fuzz Testing Tool Based on Fuzz Testing and Genetic Algorithm

SPAFuzz: Web Security Fuzz Testing Tool Based on Fuzz Testin...

引用

Consumer Electronics and Computer engineering (ICCECE), 2021 IEEE International Conference on

作者： Jiang Lin Weiyu Dong School of Computer Science and Artificial Intelligence Zhengzhou University Zhengzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Information Engineering University Zhengzhou China

Fuzzing is one of the most effective methods currently available for detecting web vulnerabilities. However, traditional fuzzing suffers from issues such as low coverage and limited diversity in test cases. To address these issues, we propose a way to generate test cases based on dynamic feature libraries and attack models by analysing the characteristics of SQL and XSS. Additionally, we introduce a genetic algorithm to guide the population's evolution by monitoring the state changes of the web application. Furthermore, we improved the selection phase of the genetic algorithm to optimally deform multiple iterations for use cases with low fitness values in order to preserve the population diversity to expand the attack capability of the test cases and based on this the SPAFuzz fuzzy testing tool was implemented. Experimental results show that SPAFuzz is able to detect more network vulnerabilities than Sqlmap and Powerfuzzer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RDGFuzz: A directed greybox fuzzing optimization method based on Rich-Branch nodes 6

RDGFuzz: A directed greybox fuzzing optimization method base...

引用

6th International Conference on Electronic Information Technology and Computer engineering, EITCE 2022

作者： Wu, Zejun Lu, Li Jia, Qiong Chen, Zhihao State Key Laboratory of Mathematical Engineering and advanced Computing Zheng zhou China National Local Joint Engineering Laboratory of Network Space Security Technology Zheng zhou China Beijing Institute of Computer Technology and Application BeiJing China

ISBN: (纸本)9781450397148

Directed fuzzing technology is one of the key technologies to quickly reach a specific location of software, and to conduct targeted testing or bug recurrence. However, directed fuzzing technology has some problems, such as unreasonable seed energy allocation, low code coverage and incomplete testing. To solve the above problems, this paper proposes an optimization method of directed fuzzing based on Rich-Branch nodes. In this method, the concept of Rich-Branch nodes is defined and the algorithm of extracting Rich-Branch nodes is given. The optimization method collects the coverage information of the target program in the running process, calculates the weights of covered functions and nodes in real time by combining CG and CFG of the target program, and generates a list of Rich-Branch nodes. According to the weights of Rich-Branch nodes, the seed energy allocation algorithm of AFLGo is optimized and improved. Compared with AFLGo, this optimization method improves the average code coverage of each targeted point by 56.79%, and has the same target reaching ability as AFLGo. © 2022 Association for computing Machinery.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Ultra-low power MoS2 optoelectronic synapse with wavelength sensitivity for color target recognition

引用

Science China(Information Sciences) 2025年第4期68卷 187-196页

作者： Bo WEI Yabo CHEN Xiaotong HAN Yan KANG Bujia LIANG Cheng LI Xiaokuo YANG Liang FANG Yuanxi PENG Institute for Quantum Information & State Key Laboratory of High Performance Computing College of ComputerNational University of Defense Technology Fundamentals Department Air Force Engineering University College of Advanced Interdisciplinary Studies National University of Defense Technology Institute of Quantum Information Science and Technology College of ScienceNational University of Defense Technology College of Computer National University of Defense Technology

Optoelectronic synapses that integrate visual perception and pre-processing hold significant potential for neuromorphic vision systems（NVSs）. However, due to a lack of wavelength sensitivity, existing NVS mainly focuses on gray-scale image processing, making it challenging to recognize color images. Additionally, the high power consumption of optoelectronic synapses, compared to the 10 fJ energy consumption of biological synapses, limits their broader application. To address these challenges, an energy-efficient NVS capable of color target recognition in a noisy environment was developed,utilizing a MoS2optoelectronic synapse with wavelength sensitivity. Benefiting from the distinct photon capture capabilities of 450, 535, and 650 nm light, the optoelectronic synapse exhibits wavelength-dependent synaptic plasticity, including excitatory postsynaptic current（EPSC）, paired-pulse facilitation（PPF）, and long-term plasticity（LTP）. These properties can effectively mimic the visual memory and color discrimination functions of the human vision system. Results demonstrate that the NVS, based on MoS2optoelectronic synapses, can eliminate the color noise at the sensor level, increasing color image recognition accuracy from 50% to 90%. Importantly, the optoelectronic synapse operates at a low voltage spike of0.0005 V, consuming only 0.075 fJ per spike, surpassing the energy efficiency of both existing optoelectronic and biological synapses. This ultra-low power, color-sensitive device eliminates the need for color filters and offers great promise for future deployment in filter-free NVS.

关键词： optoelectronic synapse neuromorphic vision system color recognition 2D materials image pre-processing

来源：评论

学校读者我要写书评

暂无评论

Can We Half the Work with Double Results: Rethinking Machine Learning Algorithms for Network Intrusion Detection System 9

Can We Half the Work with Double Results: Rethinking Machine...

引用

9th International Conference on advanced Cloud and Big Data, CBD 2021

作者： Li, Shuren Lu, Yifei Li, Jingqi Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210096 China State Key Lab of Mathematical Engineering and Advanced Computing Wuxi214215 China

ISBN: (纸本)9781665407458

Machine Learning algorithms have been wildly applied in the intrusion detection system(IDS). However, in the IoT environment where the resources are limited and the flow data is of huge amount, we need more efficient and effective ML algorithms to train the detection models. Aiming to have comprehensive performance indicators of the ML algorithms, we compared 15 machine learning for both binary classification and Multi-classification under the criterion of IoT traffic circumstance by indicators in temporal dimension and spatial dimension. We finally suggested using non-linear algorithms, especially tree algorithms training or retraining models to identify malicious network traffic in the IoT IDS. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Pruned-F1DCN: A lightweight network model for traffic classification 22

Pruned-F1DCN: A lightweight network model for traffic classi...

引用

Proceedings of the 2022 International Conference on Cyber Security

作者： Ruo nan Wang Jin long Fei Rong kai Zhang State Key Laboratory of Mathematical Engineering and Advanced Computing PLA Strategic Support Force Information Engineering University Zhengzhou China China

ISBN: (纸本)9798400700132

With the continuous development of deep learning, deep neural networks are gradually applied to traffic classification problems. However, the large network structure and parameter number of deep neural networks hinder the application on edge computing devices. Reducing network scale helps relieve computational pressure, this paper proposes a lightweight traffic classification model to provide reliable accuracy and reduce the consumption of computing resources. In this work, we design an F1DCN network, which takes full advantage of the convolution layer parameters and the convolution kernel field of view. The lightweight approach effectively improves the classification performance and saves massive parameters. The model pruning method is applied to find the optimal structure of the network. Experiments on two public datasets show that the proposed model reduce more than 80 % parameters and 45 % FLOPS compared with traditional traffic classification methods, and maintaining more than 95 % classification accuracy.

关键词： Convolutional neural network Lightweight Model pruning Traffic classification

来源：评论

学校读者我要写书评

暂无评论

Tailor : Datacenter Load Balancing for Accelerating Distributed Deep Learning 9

Tailor : Datacenter Load Balancing for Accelerating Distribu...

引用

9th International Conference on advanced Cloud and Big Data, CBD 2021

作者： Xu, Zhengzhi Lu, Yifei Li, Jingqi Ma, Xu Qian, Lei Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210096 China State Key Lab of Mathematical Engineering and Advanced Computing Wuxi214215 China

ISBN: (纸本)9781665407458

Accelerating Distributed Deep Learning draws increasing attention recently. Existing solutions like gradient compression, pipelining computation/communication, flow scheduling based on gradient disparities, neglect load balancing for Distributed Deep Learning (DDL) flows in DataCenter Network. In this paper, we review the PS traffic pattern in usual DDL training and propose that minimizing tail Flow Completion Time (FCT) of DDL flows is objective for DDL traffic Load Balancing. Besides, traffics of DDL differ from traditional DataCenter in temporal and spatial distribution. Current DCN Load Balancing become unadaptable to optimization requirements of DDL traffic, so we propose Tailor, a brand new load balancing scheme for DDL traffics training in DCN. Tailor is a solution without complex switch modification that sufficiently leverages the known parameter amount of DDL flows to discover congestion and reroutes by ECMP-like hash function to compensate bandwidth for slower flows. With large-scale simulation, we validate the effectiveness of Tailor. Tailor behaves well in both symmetric and asymmetric topology. It reduces time cost of DDL training by decreasing about 20-30% tail FCT than other load balancing mechanisms. © 2022 IEEE.

关键词： Deep learning

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：