检索结果-内蒙古大学图书馆

Large language model and domain-specific model collaboration for smart education

Frontiers of Information technology & Electronic Engineering 2024年第3期25卷 333-341页

作者： Yawei LUO Yi YANG School of Software Technology Zhejiang UniversityNingbo 315048China College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China

In this paper,we introduce the large language model and domain-specific model collaboration(LDMC)framework designed to enhance smart *** LDMC framework leverages the comprehensive and versatile knowledge of large domain-general models,combines it with the specialized and disciplinary knowledge from small domainspecific models(DSMs),and incorporates pedagogy knowledge from learning theory *** integration yields multiple knowledge representations,fostering personalized and adaptive educational *** explore various applications of the LDMC framework in the context of smart education.

关键词： smart language knowledge

来源：评论

学校读者我要写书评

暂无评论

Towards optimized tensor code generation for deep learning on sunway many-core processor

引用

Frontiers of computer science 2024年第2期18卷 1-15页

作者： Mingzhen LI Changxi LIU Jianjin LIAO Xuegui ZHENG Hailong YANG Rujun SUN Jun XU Lin GAN Guangwen YANG Zhongzhi LUAN Depei QIAN State Key Laboratory of Software Development Environment Beijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China National University of Singapore Singapore 119077Singapore State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214000China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing 100854China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China

The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application *** the existing deep learning compilers,TVM is well known for its efficiency in code generation and optimization across diverse hardware *** the meanwhile,the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning *** paper combines the trends in these two ***,we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as *** addition,we leverage the architecture features during the compilation such as core group for massive parallelism,DMA for high bandwidth memory transfer and local device memory for data locality,in order to generate efficient codes for deep learning workloads on *** experiment results show that the codes generated by swTVM achieve 1.79x improvement of inference latency on average compared to the state-of-the-art deep learning framework on Sunway,across eight representative *** work is the first attempt from the compiler perspective to bridge the gap of deep learning and Sunway processor particularly with productivity and efficiency in *** believe this work will encourage more people to embrace the power of deep learning and Sunwaymany-coreprocessor.

关键词： sunway processor deep learning compiler code generation performance optimization

来源：评论

学校读者我要写书评

暂无评论

Tissue specific prediction of N^(6)-methyladenine sites based on an ensemble of multi-input hybrid neural network

引用

BIOCELL 2022年第4期46卷 1105-1121页

作者： CANGZHI JIA DONG JIN XIN WANG QI ZHAO School of Science Dalian Maritime UniversityDalian116026China School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan114051China

N^(6)-Methyladenine is a dynamic and reversible post translational modification,which plays an essential role in various biological *** of the current inability to identify m6A-containing mRNAs,computational approaches have been developed to identify m6A sites in DNA *** to improve prediction performance,we introduced a novel ensemble computational approach based on three hybrid deep neural networks,including a convolutional neural network,a capsule network,and a bidirectional gated recurrent unit(BiGRU)with the self-attention mechanism,to identify m6A sites in four tissues of three *** a total of 11 datasets,we selected different feature subsets,after optimized from 4933 dimensional features,as input for the deep hybrid neural *** addition,to solve the deviation caused by the relatively small number of experimentally verified samples,we constructed an ensemble model through integrating five sub-classifiers based on different training *** compared through 5-fold cross-validation and independent tests,our model showed its superiority to previous methods,im6A-TS-CNN and iRNA-m6A.

关键词： M6A sites Deep hybrid neural networks Ensemble model Feature selection

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Sketch: An Efficient Solution for Threshold-t Flows Measurement in High-Speed Networks 21

Hierarchical Sketch: An Efficient Solution for Threshold-t F...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big Data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Han, Yifan Huang, He Du, Yang Sun, Yu-E Liu, Jia Xu, Hongli Soochow University School of Computer Science and Technology China Soochow University School of Rail Transportation China Nanjing University State Key Laboratory for Novel Software Technology China University of Science and Technology of China School of Computer Science and Technology China

ISBN: (纸本)9798350329223

Per-flow size measurement has wide applications in data center networks, such as flow scheduling, anomaly detection, and traffic engineering. To fit the module into limited on-chip memory and catch up with the line speed, existing works either use the bit sharing scheme to compress the flow information or require complex calculations to screen out large flows, resulting in substantial accuracy loss or heavy memory accesses, especially failing to measure medium-sized flows accurately, which are meaningful for practical applications such as usage accounting and billing. In light of this, we propose a new Hierarchical Sketch that adopts a hybrid on-chip/off-chip architecture to detect and estimate the flows whose size exceeds the threshold t (threshold-t flows for short) to cover both large and medium-sized flows. In Hierarchical Sketch, we design an on-chip bucket array together with an adaptive update scheme to record potential candidates for threshold-t flows within one memory access as well as filter out unwanted flows. Besides, the flow records are downloaded to off-chip space for high memory efficiency and supporting online queries. We also implement a prototype on the NetFPGA development platform. Experimental results show that Hierarchical Sketch is up to 72.61% more accurate and 245% faster than the best baseline. © 2023 IEEE.

关键词： HIgh speed networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Machine Learning for Real-Time Plant Replication in Embedded Systems 50

Enhanced Machine Learning for Real-Time Plant Replication in...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Chowdhury, Abhisek Jung, Jane Kuo, Matthew M.Y. Sinha, Roopak Computer Science and Software Engineering Department Auckland University of Technology Auckland New Zealand School of IT Deakin University Melbourne Australia

ISBN: (纸本)9781665464543

This paper examines the use of supervised machine learning to construct a digital twin model replicating a physical plant. An inverted pendulum simulation has been used as a case study. A comparative study was conducted on single-step and multi-step Dense models, Convolutional Neural Network (CNN), Recurrent Neural Net (RNN), and a Residual Neural Net (RNN2) models to investigate the most appropriate model for replicating the plant model. The study found that single-step models were consistently more accurate than multi-step models due to single-step model’s iterative nature. Whereas, multi-step models were better at revealing prediction patterns and identifying causes for large deviations. The best-performing model was the RNN2 model, however, signs of overfitting were observed. In general, all models were able to take into account minor random actuation, however, large changes such as the pendulum falling over caused the models to behave sporadically. © 2024 IEEE.

关键词： Inverted pendulum

来源：评论

学校读者我要写书评

暂无评论

Trustworthy decentralized collaborative learning for edge intelligence:A survey

引用

High-Confidence Computing 2023年第3期3卷 89-103页

作者： Dongxiao Yu Zhenzhen Xie Yuan Yuan Shuzhen Chen Jing Qiao Yangyang Wang Yong Yu Yifei Zou Xiao Zhang School of Computer Science and Technology Shandong UniversityQingdao 266237China School of Software&Joint SDU-NTU Centre for Artificial Intelligence Research(C-FAIR) Shandong UniversityQingdao 266237China School of Computer Science Shaanxi Normal UniversityXi’an 710062China

Edge intelligence is an emerging technology that enables artificial intelligence on connected systems and devices in close proximity to the data *** collaborative learning(DCL)is a novel edge intelligence technique that allows distributed clients to cooperatively train a global learning model without revealing their *** has a wide range of applications in various domains,such as smart city and autonomous ***,DCL faces significant challenges in ensuring its trustworthiness,as data isolation and privacy issues make DCL systems vulnerable to adversarial attacks that aim to breach system confidentiality,undermine learning reliability or violate data ***,it is crucial to design DCL in a trustworthy manner,with a focus on security,robustness,and *** this survey,we present a comprehensive review of existing efforts for designing trustworthy DCL systems from the three key aformentioned aspects:security,robustness,and *** analyze the threats that affect the trustworthiness of DCL across different scenarios and assess specific technical solutions for achieving each aspect of trustworthy DCL(TDCL).Finally,we highlight open challenges and future directions for advancing TDCL research and practice.

关键词： Trustworthy machine learning Decentralized collaborative learning Security Robustness Privacy

来源：评论

学校读者我要写书评

暂无评论

Color Image Encryption Based on 4D Hyperchaotic System and RSA Algorithm Combined Scrambling and Diffusion 5

Color Image Encryption Based on 4D Hyperchaotic System and R...

引用

5th International Conference on Industrial Artificial Intelligence, IAI 2023

作者： Dong, Zhiqing Zhang, Zhao Zhou, Hongyan Chen, Xue-Bo University of Science and Technology Liaoning School of Computer Science and Software Engineering Anshan China University of Science and Technology Liaoning School of Electronics and Information Engineering Anshan China

ISBN: (纸本)9798350325294

In this paper, a color image encryption scheme based on 4D hyperchaos system and RSA algorithm is proposed. Firstly, RSA algorithm is used to generate the initial value of 4D hyperchaotic system, and the key stream is iteratively generated. Then, the color image is divided into RGB three channels. In order to change the position of image pixels, Arnold scrambling is performed on the image. Finally, simultaneous scrambling and diffusion algorithms are used to encrypt the preprocessed images for a second time. Experimental results show that the encryption scheme proposed in this paper is effective. Compared with the existing algorithms, this encryption scheme improves the encryption efficiency, has strong anti-aggression and robustness. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

A new method to analyze visual efficiency in interactive web environment

A new method to analyze visual efficiency in interactive web...

引用

2023 International Conference on computer Graphics, Artificial Intelligence, and Data Processing, ICCAID 2023

作者： Lv, Wen Li, Tingting Xie, Zhenping School of Artificial Intelligence and Computer Science Jiangnan University China Jiangsu Key Laboratory of Media Design and Software Technology China

ISBN: (纸本)9781510677685

Interactive web interfaces are widely used, yet users often struggle to discover important and useful information. Psychologists have pointed out that in the process of human visual perception, the global topological characteristics of objects will be perceived first. In this study, we propose a cognitive experiment system to explore what object properties affect visual efficiency in interactive web environments. Our experimental results showed that, first, if a small number of colors are allocated to different objects, these objects could be more effectively memorized than no color or too many colors. Second, in static single-page, different topology structures will not cause apparently different visual attraction, however, topological structural differences could be stronger memorized. Third, in dynamic HTML, the motion changes will induce stronger visual attention and memory intensity, than their own topology changes. Subsequently, we verified the feasibility of the experiment system in real webpages and demonstrated that the above results can theoretically guide better web interaction design works with less cognitive load of users, higher operation efficiency and more natural user experience. In addition, some design reference suggestions are also provided in our study. © 2024 SPIE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Deeply‐Recursive Attention Network for video steganography

引用

CAAI Transactions on Intelligence technology 2023年第4期8卷 1507-1523页

作者： Jiabao Cui Liangli Zheng Yunlong Yu Yining Lin Huajian Ni Xin Xu Zhongfei Zhang College of Computer Science and Technology Zhejiang UniversityHangzhouChina School of Software Technology Zhejiang UniversityNingboChina College of Information Science and Electronic Engineering Zhejiang UniversityHangzhouChina Shanghai SUPREMIND Technology Co. Ltd.ShanghaiChina College of Intelligence Science and Technology National University of Defense TechnologyChangshaChina Department of Computer Science Binghamton UniversityBinghamtonNew YorkUSA

Video steganography plays an important role in secret communication that conceals a secret video in a cover video by perturbing the value of pixels in the cover *** is the first and foremost requirement of any steganographic *** by the fact that human eyes perceive pixel perturbation differently in different video areas,a novel effective and efficient Deeply‐Recursive Attention Network(DRANet)for video steganography to find suitable areas for information hiding via modelling spatio‐temporal attention is *** DRANet mainly contains two important components,a Non‐Local Self‐Attention(NLSA)block and a Non‐Local Co‐Attention(NLCA)***,the NLSA block can select the cover frame areas which are suitable for hiding by computing the correlations among inter‐and intra‐cover *** NLCA block aims to effectively produce the enhanced representations of the secret frames to enhance the robustness of the model and alleviate the influence of different areas in the secret ***,the DRANet reduces the model parameters by performing similar operations on the different frames within an input video *** results show the proposed DRANet achieves better performance with fewer parameters than the state‐of‐the‐art competitors.

关键词： data privacy video processing

来源：评论

学校读者我要写书评

暂无评论

PredRacer: Predictively Detecting Data Races in Android Applications 31

PredRacer: Predictively Detecting Data Races in Android Appl...

引用

31st IEEE International Conference on software Analysis, Evolution and Reengineering, SANER 2024

作者： Guo, Xin Qi, Xiaofang Li, Yanhui Wu, Chao School of Computer Science and Engineering Southeast University China Nanjing University State Key Laboratory for Novel Software Technology China

ISBN: (纸本)9798350330663

Android platform offers a hybrid concurrency model encompassing multi-threading and asynchronous messaging for concurrent programming. The model is powerful but complex, making it difficult for developers to analyze concurrent behaviors. Data race, a prevalent concurrency defect in real-world Android applications, often results in abnormal executions of mobile applications, even crashes. Despite quite a few studies on detecting data races, it still suffers from high false positives with static analysis techniques and high false negatives with dynamic analysis techniques. To address this issue, this paper presents a predictive approach, PredRacer, for detecting data races in Android applications. It first captures an execution trace of an Android application, and then reorders the events within the trace based on partial orders. Finally, it checks the feasibility of the generated event sequence, which contains a potential data race. PredRacer increases the search scope and reduces false negatives while mitigating false positives by incorporating the happen-before relations specific to the Android concurrency model. The effectiveness of PredRacer is evaluated using the BenchERoid data set. Experimental results demonstrate that PredRacer achieves high precision, recall, and F1 score, outperforming the state-of-the-art techniques. A collection of 20 open-source Android applications is further utilized to assess the effectiveness of PredRacer, and an evaluation of 300 wild apps is conducted to assess its efficiency and scalability. © 2024 IEEE.

关键词： Static analysis

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：