检索结果-内蒙古大学图书馆

8th International Conference on Computing and data engineering, ICCDE 2022

作者： Li, Jie Zhang, Tian-Xiang Li, Leixiao Kang, Zefeng Niu, Tieming Gao, Jing College of Data Science and Application Inner Mongolia University of Technology China Inner Mongolia Autonomous Reg. Software Serv. Eng. Technology Research Center Based on Big Data Hohhot China College of Computer and Information Engineering Inner Mongolia Agricultural University Hohhot China

ISBN: (纸本)9781450395717

The availability of cloud services is an important performance index of cloud platform. It is the premise and basis for a cloud platform to provide services. Aiming at the problem of insufficient reliability of cloud services in university data centers, this paper proposes a high available and decentralized cloud platform scheme based on OpenStack for university micro data center. Firstly, the scheme sets the super fusion of the network layer and detects the state through URL location, which effectively avoids the single points of failure. And then, the database layer adopts multi-master design to realize the super redundant architecture and ensure the high availability. Finally, the reliability evaluation model and experiments show that the service availability of this scheme is very high. © 2022 ACM.

关键词： Platform as a Service (PaaS)

来源：评论

学校读者我要写书评

暂无评论

Source Code Summarization in the Era of Large Language Models

arXiv

引用

arXiv 2024年

作者： Sun, Weisong Miao, Yun Li, Yuekang Zhang, Hongyu Fang, Chunrong Liu, Yi Deng, Gelei Liu, Yang Chen, Zhenyu State Key Laboratory for Novel Software Technology Nanjing University Nanjing China College of Computing and Data Science Nanyang Technological University Singapore Singapore School of Computer Science and Engineering University of New South Wales Sidney Australia School of Big Data and Software Engineering Chongqing University Chongqing China

To support software developers in understanding and maintaining programs, various automatic (source) code summarization techniques have been proposed to generate a concise natural language summary (i.e., comment) for a given code snippet. Recently, the emergence of large language models (LLMs) has led to a great boost in the performance of code-related tasks. In this paper, we undertake a systematic and comprehensive study on code summarization in the era of LLMs, which covers multiple aspects involved in the workflow of LLM-based code summarization. Specifically, we begin by examining prevalent automated evaluation methods for assessing the quality of summaries generated by LLMs and find that the results of the GPT-4 evaluation method are most closely aligned with human evaluation. Then, we explore the effectiveness of five prompting techniques (zero-shot, few-shot, chain-of-thought, critique, and expert) in adapting LLMs to code summarization tasks. Contrary to expectations, advanced prompting techniques may not outperform simple zero-shot prompting. Next, we investigate the impact of LLMs’ model settings (including top_p and temperature parameters) on the quality of generated summaries. We find the impact of the two parameters on summary quality varies by the base LLM and programming language, but their impacts are similar. Moreover, we canvass LLMs’ abilities to summarize code snippets in distinct types of programming languages. The results reveal that LLMs perform suboptimally when summarizing code written in logic programming languages compared to other language types (e.g., procedural and object-oriented programming languages). Finally, we unexpectedly find that CodeLlama-Instruct with 7B parameters can outperform advanced GPT-4 in generating summaries describing code implementation details and asserting code properties. We hope that our findings can provide a comprehensive understanding of code summarization in the era of *** Codes 68-04 Copyright © 202

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for 6G:Applications,Challenges,and Opportunities

引用

engineering 2022年第1期8卷 33-41页

作者： Zhaohui Yang Mingzhe Chen Kai-Kit Wong H.Vincent Poor Shuguang Cui Department of Electronic and Electrical Engineering University College LondonLondon WC1E 6BTUK Department of Electrical and Computer Engineering Princeton UniversityPrincetonNJ 08544USA Shenzhen Research Institute of Big Data The Chinese University of Hong KongShenzhen 518172China School of Science and Engineering and Future Network of Intelligence Institute The Chinese University of Hong KongShenzhen 518172China

Standard machine-learning approaches involve the centralization of training data in a data center,where centralized machine-learning algorithms can be applied for data analysis and ***,due to privacy restrictions and limited communication resources in wireless networks,it is often undesirable or impractical for the devices to transmit data to parameter *** approach to mitigate these problems is federated learning(FL),which enables the devices to train a common machine learning model without data sharing and *** paper provides a comprehensive overview of FL applications for envisioned sixth generation(6G)wireless *** particular,the essential requirements for applying FL to wireless communications are first *** potential FL applications in wireless communications are *** main problems and challenges associated with such applications are ***,a comprehensive FL implementation for wireless communications is described.

关键词： Federated learning 6G Reconfigurable intelligent surface Semantic communication Sensing Communication and computing

来源：评论

学校读者我要写书评

暂无评论

Semi-Asynchronous Federated Learning with Trajectory Prediction for Vehicular Edge Computing

Semi-Asynchronous Federated Learning with Trajectory Predict...

引用

International Workshop on Quality of Service

作者： Yuxuan Deng Xiuhua Li Chuan Sun Qilin Fan Xiaofei Wang Victor C. M. Leung School of Big Data & Software Engineering Chongqing University Chongqing China School of Computer Science and Engineering Nanyang Technological University Singapore TKLAN College of Intelligence & Computing Tianjin University Tianjin China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen China College of Computer Science & Software Engineering Shenzhen University Shenzhen China Department of Electrical & Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798350350128

ISBN: (纸本)9798350350135

Federated learning, as a distributed machine learning paradigm, offers promising solutions for vehicular edge computing (VEC) networks. However, federated learning in VEC with classification tasks still faces two key challenges: i) Delayed data labeling hampers supervised training; ii) Dynamic vehicle behavior complicates training scheduling and model uploads to edge servers. In this paper, we propose a semi-asynchronous federated learning algorithm for VEC. Specifically, it utilizes knowledge distillation to generate soft labels from raw data for supervised training, and estimates model training and uploading time through trajectory prediction. We further logically group vehicles based on the characteristics of their dynamic behavior. We then employ synchronous aggregation within groups and asynchronous aggregation between groups to optimize model performance while reducing latency. Finally, we conduct separate comparative experiments for all components, demonstrating that each component possesses unique advantages. Experiment results show that the proposed algorithm outperforms existing schemes in terms of accuracy and latency. The code is available at: https://***/dyxcode/Semi-Asynchronous-Federated-Learning.

关键词： Training Federated learning Heuristic algorithms Predictive models Prediction algorithms data models Trajectory

来源：评论

学校读者我要写书评

暂无评论

DCML: Boosting Applying Experience of NILM with Dilated Convolution and Multi-Task Learning

DCML: Boosting Applying Experience of NILM with Dilated Conv...

引用

IEEE International Conference on Communications in China (ICCC)

作者： ZhangMengru Zhao Fan Wu Huaqing Wu Tong Liu Conghao Zhou Jun Ma Yongmin Zhang Feng Lyu School of Computer Science and Engineering Central South University Changsha China Department of Electrical and Software Engineering University of Calgary Calgary AB Canada Big Data Institute Central South University Changsha China Department of Electrical and Computer Engineering University of Waterloo Waterloo Ontario Canada Hunan Energy Big Data Intelligence Limited Changsha China

ISBN: (数字)9798350378412

ISBN: (纸本)9798350378429

Non-intrusive load monitoring (NILM) is a promising approach for recognizing various electrical equipment energy usage patterns from aggregate load data. In this paper, we investigate the development of an NILM model to achieve high recognition accuracy, ensure a small model size for lightweight implementation, and enhance its adaptability to a wide range of appliance types. Specifically, we propose a framework named DCML, which employs dilated convolution to precisely control the receptive field, allowing efficient adjustments in feature extraction granularity to meet the specific requirements of different appliances. In addition, multi-task learning techniques are incorporated to allow simultaneous recognition of multiple appliances from a single model, saving model space while ensuring high recognition accuracy. Compared to the benchmark, our model reduces the recognition mean absolute error (MAE) by $36.8 \%, 16.8 \%$, and $43.8 \%$ for fridges, microwaves, and washing machines, respectively. Furthermore, the proposed DCML can significantly save the storage space of convolutional layers when simultaneously recognizing multiple appliances.

关键词： Adaptation models Accuracy Convolution Multitasking data models Stability analysis Robustness

来源：评论

学校读者我要写书评

暂无评论

ShoppingGPT: A GPT-based Product Recommendation Dialogue System 4

ShoppingGPT: A GPT-based Product Recommendation Dialogue Sys...

引用

4th IEEE International Conference on Pattern Recognition and Machine Learning, PRML 2023

作者： Yu, Renjie Guan, Yujing Zhan, Yuancheng Guangxi University of XingJian College of Science and Liberal Arts Dept. of Computer and Information Technology Nanning China Guangxi University of Finance and Economics Dept. of School of Big Data and Artificial Intelligence Nanning China Technology of NanNing University NanNing University Dept. Global Institute of Software Nanning China

ISBN: (纸本)9798350324303

This article introduces a shopping recommendation dialogue system called ShoppingGPT, which aims to help people get comprehensive product recommendations based on individual needs and preferences. The system can leverage existing large-scale generative pre-trained models with the ability to communicate and understand human language to provide more detailed and comprehensive product recommendations through multiple conversations with users. By constructing the shopping recommendation dataset and using the large-scale language model fine-tuning methods, we successfully fine-tuned on a large-scale language model and transformed the shopping recommendation task into a sequential labeling task to adapt to our shopping recommendation dialogue system. And we design a specific method for unlabeled prompt, which uses the basic language knowledge of large-scale language models to output product information for unsupervised annotation for product recommendation. In the experiment, we evaluate several existing language model fine-tuning techniques and explore the generalization ability of the ShoppingGPT system on unlabeled samples. We also compared models before and after fine-tuning to see what the models learned from the data. In the discussion section, we provide a detailed analysis of the advantages and limitations of ShoppingGPT and its potential applications in the shopping field. In addition, we explore the potential security challenges that ShoppingGPT can pose and discuss how to address them. Finally, we discussed how to improve ShoppingGPT to make it perform better and more secure. © 2023 IEEE.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

What Makes Good In-context Demonstrations for Code Intelligence Tasks with LLMs?

arXiv

引用

arXiv 2023年

作者： Gao, Shuzheng Wen, Xin-Cheng Gao, Cuiyun Wang, Wenxuan Zhang, Hongyu Lyu, Michael R. School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering The Chinese University of Hong Kong China School of Big Data and Software Engineering Chongqing University China

Pre-trained models of source code have gained widespread popularity in many code intelligence tasks. Recently, with the scaling of the model and corpus size, large language models have shown the ability of in-context learning (ICL). ICL employs task instructions and a few examples as demonstrations, and then inputs the demonstrations to the language models for making predictions. This new learning paradigm is training-free and has shown impressive performance in various natural language processing and code intelligence tasks. However, the performance of ICL heavily relies on the quality of demonstrations, e.g., the selected examples. It is important to systematically investigate how to construct a good demonstration for code-related tasks. In this paper, we empirically explore the impact of three key factors on the performance of ICL in code intelligence tasks: the selection, order, and number of demonstration examples. We conduct extensive experiments on three code intelligence tasks including code summarization, bug fixing, and program synthesis. Our experimental results demonstrate that all the above three factors dramatically impact the performance of ICL in code intelligence tasks. Additionally, we summarize our findings and provide takeaway suggestions on how to construct effective demonstrations, taking into account these three perspectives. We also show that a carefully-designed demonstration based on our findings can lead to substantial improvements over widely-used demonstration construction methods, e.g., improving BLEU-4, EM, and EM by at least 9.90%, 175.96%, and 50.81% on code summarization, bug fixing, and program synthesis, respectively. © 2023, CC BY.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

What Makes Good In-Context Demonstrations for Code Intelligence Tasks with LLMs?

What Makes Good In-Context Demonstrations for Code Intellige...

引用

IEEE International Conference on Automated software engineering (ASE)

作者： Shuzheng Gao Xin-Cheng Wen Cuiyun Gao Wenxuan Wang Hongyu Zhang Michael R. Lyu School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering The Chinese University of Hong Kong China School of Big Data and Software Engineering Chongqing University China

关键词：

来源：评论

学校读者我要写书评

暂无评论

Slice-level Detection of Intracranial Hemorrhage on CT Using Deep Descriptors of Adjacent Slices

Slice-level Detection of Intracranial Hemorrhage on CT Using...

引用

IEEE/SP Workshop on Statistical Signal Processing (SSP)

作者： Dat T. Ngo Thao T.B. Nguyen Hieu T. Nguyen Dung B. Nguyen Ha Q. Nguyen Hieu H. Pham Vingroup Big Data Institute Hanoi Vietnam VinBigData JSC Vingroup Big Data Institute Hanoi Vietnam VinUni-Illinois Smart Health Center College of Engineering & Computer Science VinUniversity Hanoi Vietnam

We propose for the first time a new strategy to train slice-level classifiers on CT scans based on the descriptors of the adjacent slices along the axis. In particular, each of which is extracted through a convolutional neural network (CNN). This method is applicable to CT datasets with per-slice labels such as the RSNA Intracranial Hemorrhage (ICH) dataset, which aims to predict the presence of ICH and classify it into 5 different sub-types. We obtain a single model in the top 4% best-performing solutions of the RSNA ICH challenge, where model ensembles are allowed. Experiments also show that the proposed method significantly outperforms the baseline model on CQ500. The proposed method is general and can be applied to other 3D medical diagnosis tasks such as MRI imaging. To encourage new advances in the field, we will make our codes and pre-trained model available upon acceptance of the paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning

arXiv

引用

arXiv 2024年

作者： Zeng, Runhao Zhou, Dingjie Liang, Qiwei Liu, Junlin Li, Hui Huang, Changxin Li, Jianqiang Hu, Xiping Sun, Fuchun Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Mechatronics and Control Engineering Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science and Technology Tsinghua University China

Learning behavior in legged robots presents a significant challenge due to its inherent instability and complex constraints. Recent research has proposed the use of a large language model (LLM) to generate reward functions in reinforcement learning, thereby replacing the need for manually designed rewards by experts. However, this approach, which relies on textual descriptions to define learning objectives, fails to achieve controllable and precise behavior learning with clear directionality. In this paper, we introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Specifically, we first process videos containing the target behaviors, converting the motion information of individuals in the videos into keypoint trajectories represented as coordinates through a video2text transforming module. These trajectories are then fed into an LLM to generate the reward function, which in turn is used to train the policy. To enhance the quality of the reward function, we develop a video-assisted iterative reward refinement scheme that visually assesses the learned behaviors and provides textual feedback to the LLM. This feedback guides the LLM to continually refine the reward function, ultimately facilitating more efficient behavior learning. Experimental results on tasks involving bipedal and quadrupedal robot motion control demonstrate that our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score. More importantly, by switching video inputs, we find our method can rapidly learn diverse motion behaviors such as walking and running. Copyright © 2024, The Authors. All rights reserved.

关键词： Robots

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：