检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Mengjuan Liu, Chenyang Yang, Yunfan Liu, Jiang Jing, Mohan Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu China

Recently, utilizing deep neural networks to build the open-domain dialogue models has become a hot topic. However, the responses generated by these models suffer from many problems such as responses not being contextualized and tend to generate generic responses that lack information content, damaging the user's experience seriously. Therefore, many studies try introducing more information into the dialogue models to make the generated responses more vivid and informative. Unlike them, this paper improves the quality of generated responses by learning the implicit pattern information between contexts and responses in the training samples. In this paper, we first build an open-domain dialogue model based on the pre-trained language model (i.e., GPT-2). And then, an improved scheduled sampling method is proposed for pre-trained models, by which the responses can be used to guide the response generation in the training phase while avoiding the exposure bias problem. More importantly, we design a response-aware mechanism for mining the implicit pattern information between contexts and responses so that the generated replies are more diverse and approximate to human replies. Finally, we evaluate the proposed model (RAD) on the Persona-Chat and DailyDialog datasets;and the experimental results show that our model outperforms the baselines on most automatic and manual metrics. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Software Module Clustering Using the Hierarchical Clustering Combination Method 7

Software Module Clustering Using the Hierarchical Clustering...

引用

7th International Conference on Cloud Computing and Big data Analytics, ICCCBDA 2022

作者： Xia, Hong Zhang, Yongkang Chen, Yanping Zhang, Hengshan Wang, Zhongmin Wang, Fengwei School of Computer Science and Technology Xi'An Univ. of P. and Telecom. Shaanxi Key Lab. of Network Data Analysis and Intelligent Processing Xi'an China Xi'An University of Posts and Telecommunications School of Computer Science and Technology Xi'an China ZTECorporation Shenzhen China

ISBN: (纸本)9781665487115

The scale of software applications has increased dramatically. Hierarchical clustering is a good method for modular recovery of software architecture. Because the different evaluation criteria of software types and clustering results, a single hierarchical clustering algorithm cannot integrate the number of clusters, arbitrary decision-making, recovery quality and other indicators on different evaluation standards, there is no comprehensive clustering algorithm selection method. We propose a hierarchical clustering combination algorithm and use principal component analysis to combine the results of multiple hierarchical clusters, the combined result retain the basic information of each clustering algorithm as much as possible. The experimental results show that compared with the single software hierarchical clustering method and other combined methods, the result of our method is closer to expert decomposition, and it has good performance on a variety of indicators. © 2022 IEEE.

关键词： Cloud computing Software architecture Clustering methods Software algorithms Decision making Clustering algorithms Big data

来源：评论

学校读者我要写书评

暂无评论

Stabilization of switched systems with unstable modes via mode-partition-dependent ADT

引用

Journal of the Franklin Institute 2023年第2期360卷 1308-1326页

作者： Jin, Cui-Li Wang, Qing-Guo Wang, Rui Wu, Di Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education and School of Control Science and Engineering Dalian University of Technology Dalian116024 China Institute of Artificial Intelligence and Future Networks Beijing Normal University at ZhuhaiGuangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College Zhuhai519087 China Key Laboratory of Advanced Technology for Aerospace Vehicles Liaoning Province and School of Aeronautics and Astronautics Dalian University of Technology Dalian116024 China

This paper concerns the stability of switched systems orchestrating between unstable modes. First, a mode partition is applied to select stabilizing switching from the switching between modes from different subsets. Second, a piecewise Lyapunov-like function is applied to decline at stabilizing switching times. Then, the stability criteria build on mode-partition-dependent average dwell time by collecting enough stabilizing switching behavior to stabilize the destabilizing switching behavior and unstable modes. Finally, the simulation verification shows the feasibility and effectiveness of the method. © 2022 The Franklin Institute

关键词： Stability criteria

来源：评论

学校读者我要写书评

暂无评论

NeuVSA: A Unified and Efficient Accelerator for Neural Vector Search

NeuVSA: A Unified and Efficient Accelerator for Neural Vecto...

引用

IEEE Symposium on High-Performance Computer Architecture

作者： Ziming Yuan Lei Dai Wen Li Jie Zhang Shengwen Liang Ying Wang Cheng Liu Huawei Li Xiaowei Li Jiafeng Guo Peng Wang Renhai Chen Gong Zhang State Key Lab of Processors Institute of Computing TechnologyCAS University of Chinese Academy of Sciences School of Computer and Information Technology Shanxi University School of Computer Science Peking University Zhongguancun National Laboratory Beijing Key Lab of Network Data Science and Technology Institute of Computing Technology CAS Huawei Technologies Co. Ltd. China

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Neural Vector Search (NVS) has exhibited superior search quality over traditional key-based strategies for information retrieval tasks. An effective NVS architecture requires high recall, low latency, and high throughput to enhance user experience and cost-efficiency. However, implementing NVS on existing neural network accelerators and vector search accelerators is sub-optimal due to the separation between the embedding stage and vector search stage at both algorithm and architecture levels. Fortunately, we unveil that Product Quantization (PQ) opens up an opportunity to break separation. However, existing PQ algorithms and accelerators still focus on either the embedding stage or the vector search stage, rather than both simultaneously. Simply combining existing solutions still follows the beaten track of separation and suffers from insufficient parallelization, frequent data access conflicts, and the absence of scheduling, thus failing to reach optimal recall, latency, and throughput. To this end, we propose a unified and efficient NVS accelerator dubbed NeuVSA based on algorithm and architecture co-design philosophy. Specifically, on the algorithm level, we propose a learned PQ-based unified NVS algorithm that consolidates two separate stages into the same computing and memory access paradigm. It integrates an end-to-end joint training strategy to learn the optimal codebook and index for enhanced recall and reduced PQ complexity, thus achieving smoother acceleration. On the architecture level, we customize a homogeneous NVS accelerator based on the unified NVS algorithm. Each sub-accelerator is optimized to exploit all parallelism exposed by unified NVS, incorporating a structured index assignment strategy and an elastic on-chip buffer to alleviate buffer conflicts for reduced latency. All sub-accelerators are coordinated using a hardware-aware scheduling strategy for boosted throughput. Experimental results show that the joint training strategy improves recall

关键词： Training Quantization (signal) Philosophical considerations Graphics processing units Computer architecture Throughput Vectors User experience System-on-chip Indexes

来源：评论

学校读者我要写书评

暂无评论

A Digitally assisted nonlinearity suppression architecture using over-the-air beam cancelation

A Digitally assisted nonlinearity suppression architecture u...

引用

作者： Mu, Qin Li, Nanxi Chen, Cong Wei, Xiaozheng Wen, Rong Wu, Muqing Li, Xiang Liu, Ying School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China National Key Lab of Science and Technology on Communications University of Electronic Science and Technology of China Chengdu China School of Network and Communication Engineering Chengdu Technological University Chengdu China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing China

Using a large number of power amplifiers brings serious nonlinear distortion to 5G communication systems, which becomes a challenging problem for conventional digital predistortion (DPD) to linearize signals. To address this challenge, we propose a digitally assisted nonlinearity suppression architecture for applications in multiple antenna arrays. In this architecture, we use an auxiliary array to generate a nonlinear cancelation signal to cancel with the main beam at the receiving end. We explore a two-step method to model the nonlinear signal and combine neural network to complete the modeling. In addition, we introduce a novel method for estimating and tracking the channel to update the model coefficients. To verify the proposed methods, we design a scene and compare the performance of our architecture with that of conventional DPD. Our experiments demonstrate that our proposed methods can significantly enhance the adjacent channel power leakage ratio performance by 12 dB while also optimizing in-band distortion. Moreover, our architecture outperforms conventional DPD approaches even with enhanced distortion. © 2023 John Wiley & Sons Ltd.

关键词： Power amplifiers

来源：评论

学校读者我要写书评

暂无评论

network Security Situation Assessment Method Based on Absorbing Markov Chain

Network Security Situation Assessment Method Based on Absorb...

引用

2022 International Conference on networking and network Applications, NaNA 2022

作者： Gao, Hongbin Wang, Shangxing Zhang, Hongbin Liu, Bin Zhao, Dongmei Liu, Zhen Hebei University of Science and Technology School of Information Science and Engineering Shijiazhuang China Hebei University of Science and Technology School of Information Science and Engineering Hebei Key Laboratory of Network and Information Security Shijiazhuang China Hebei University of Science and Technology School of Economics and Management Research Center of Big Data and Social Computing Shijiazhuang China Hebei Normal University Hebei Key Laboratory of Network and Information Security Shijiazhuang China

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

This paper has a new network security evaluation method as an absorbing Markov chain-based assessment method. This method is different from other network security situation assessment methods based on graph theory. It effectively refinement issues such as poor objectivity of other methods, incomplete consideration of evaluation factors, and mismatching of evaluation results with the actual situation of the network. Firstly, this method collects the security elements in the network. Then, using graph theory combined with absorbing Markov chain, the threat values of vulnerable nodes are calculated and sorted. Finally, the maximum possible attack path is obtained by blending network asset information to determine the current network security status. The experimental results prove that the method fully considers the vulnerability and threat node ranking and the specific case of system network assets, which makes the evaluation result close to the actual network situation. © 2022 IEEE.

关键词： network security

来源：评论

学校读者我要写书评

暂无评论

ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers

arXiv

引用

arXiv 2024年

作者： Jiang, Yanfeng Sun, Ning Xie, Xueshuo Yang, Fei Li, Tao College of Computer Science Nankai University Tianjin China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China Zhejiang Lab Zhejiang Hangzhou China Haihe Lab of ITAI Tianjin China

Vision Transformers (ViTs) have exhibited exceptional performance across diverse computer vision tasks, while their substantial parameter size incurs significantly increased memory and computational demands, impeding effective inference on resource-constrained devices. Quantization has emerged as a promising solution to mitigate these challenges, yet existing methods still suffer from significant accuracy loss at low-bit. We attribute this issue to the distinctive distributions of post-LayerNorm and post-GELU activations within ViTs, rendering conventional hardware-friendly quantizers ineffective, particularly in low-bit scenarios. To address this issue, we propose a novel framework called Activation-Distribution-Friendly post-training Quantization for Vision Transformers, ADFQ-ViT. Concretely, we introduce the Per-Patch Outlier-aware Quantizer to tackle irregular outliers in post-LayerNorm activations. This quantizer refines the granularity of the uniform quantizer to a per-patch level while retaining a minimal subset of values exceeding a threshold at full-precision. To handle the non-uniform distributions of post-GELU activations between positive and negative regions, we design the Shift-Log2 Quantizer, which shifts all elements to the positive region and then applies log2 quantization. Moreover, we present the Attention-score enhanced Module-wise Optimization which adjusts the parameters of each quantizer by reconstructing errors to further mitigate quantization error. Extensive experiments demonstrate ADFQ-ViT provides significant improvements over various baselines in image classification, object detection, and instance segmentation tasks at 4-bit. Specifically, when quantizing the ViT-B model to 4-bit, we achieve a 10.23% improvement in Top-1 accuracy on the ImageNet dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Zero Watermarking Algorithm for Medical Image Based on Resnet50-DCT

引用

Computers, Materials & Continua 2023年第4期75卷 293-309页

作者： Mingshuai Sheng Jingbing Li Uzair Aslam Bhatti Jing Liu Mengxing Huang Yen-Wei Chen School of Information and Communication Engineering Hainan UniversityHaikou570228China State Key Laboratory of Marine Resource Utilization in the South China Sea Hainan UniversityHaikou570228China School of Computer Science and Technology Hainan UniversityHaikou570228China Research Center for Healthcare Data Science Zhejiang LabHangzhou311121China Graduate School of Information Science and Engineering Ritsumeikan UniversityKyoto5258577Japan

Medical images are used as a diagnostic tool, so protecting theirconfidentiality has long been a topic of study. From this, we propose aResnet50-DCT-based zero watermarking algorithm for use with medicalimages. To begin, we use Resnet50, a pre-training network, to draw out thedeep features of medical images. Then the deep features are transformedby DCT transform and the perceptual hash function is used to generatethe feature vector. The original watermark is chaotic scrambled to get theencrypted watermark, and the watermark information is embedded into theoriginal medical image by XOR operation, and the logical key vector isobtained and saved at the same time. Similarly, the same feature extractionmethod is used to extract the deep features of the medical image to be testedand generate the feature vector. Later, the XOR operation is carried outbetween the feature vector and the logical key vector, and the encryptedwatermark is extracted and decrypted to get the restored watermark;thenormalized correlation coefficient (NC) of the original watermark and therestored watermark is calculated to determine the ownership and watermarkinformation of the medical image to be tested. After calculation, most ofthe NC values are greater than 0.50. The experimental results demonstratethe algorithm’s robustness, invisibility, and security, as well as its ability toaccurately extract watermark information. The algorithm also shows goodresistance to conventional attacks and geometric attacks.

关键词： Medical images deep residual network resnet50-DCT privacy protection robustness security

来源：评论

学校读者我要写书评

暂无评论

Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method

arXiv

引用

arXiv 2023年

作者： Liu, Yu-An Zhang, Ruqing Chen, Wei Guo, Jiafeng Fan, Yixing de Rijke, Maarten Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS University of Chinese Academy of Sciences Beijing China University of Amsterdam Amsterdam Netherlands

Neural ranking models (NRMs) and dense retrieval (DR) models have given rise to substantial improvements in overall retrieval performance. In addition to their effectiveness, and motivated by the proven lack of robustness of deep learning-based approaches in other areas, there is growing interest in the robustness of deep learning-based approaches to the core retrieval problem. Adversarial attack methods that have so far been developed mainly focus on attacking NRMs, with very little attention being paid to the robustness of DR models. In this paper, we introduce the adversarial retrieval attack (AREA) task. The AREA task is meant to trick DR models into retrieving a target document that is outside the initial set of candidate documents retrieved by the DR model in response to a query. We consider the decision-based black-box adversarial setting, which is realistic in real-world search engines. To address the AREA task, we first employ existing adversarial attack methods designed for NRMs. We find that the promising results that have previously been reported on attacking NRMs, do not generalize to DR models: these methods underperform a simple term spamming method. We attribute the observed lack of generalizability to the interaction-focused architecture of NRMs, which emphasizes fine-grained relevance matching. DR models follow a different representation-focused architecture that prioritizes coarse-grained representations. We propose to formalize attacks on DR models as a contrastive learning problem in a multi-view representation space. The core idea is to encourage the consistency between each view representation of the target document and its corresponding viewer via view-wise supervision signals. Experimental results demonstrate that the proposed method can significantly outperform existing attack strategies in misleading the DR model with small indiscernible text perturbations. Copyright © 2023, The Authors. All rights reserved.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Adfq-Vit: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers

SSRN

引用

SSRN 2024年

关键词： Chemical activation

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：