检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Kumar, Mohit Valentinitsch, Alexander Fuchs, Magdalena Brucker, Mathias Bowles, Juliana Husakovic, Adnan Abbas, Ali Moser, Bernhard A. Faculty of Computer Science and Electrical Engineering University of Rostock Germany Software Competence Center Hagenberg GmbH HagenbergA-4232 Austria School of Computer Science University of St Andrews United Kingdom Primetals Technologies Austria GmbH LinzA-4031 Austria Institute of Signal Processing Johannes Kepler University Linz Austria

This paper develops a novel mathematical framework for collaborative learning by means of geometrically inspired kernel machines which includes statements on the bounds of generalisation and approximation errors, and sample complexity. For classification problems, this approach allows us to learn bounded geometric structures around given data points and hence solve the global model learning problem in an efficient way by exploiting convexity properties of the related optimisation problem in a Reproducing Kernel Hilbert Space (RKHS). In this way, we can reduce classification problems to determining the closest bounded geometric structure from a given data point. Further advantages that come with our solution is that our approach does not require clients to perform multiple epochs of local optimisation using stochastic gradient descent, nor require rounds of communication between client/server for optimising the global model. We highlight that numerous experiments have shown that the proposed method is a competitive alternative to the state-of-the-art. © 2024, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

StencilMART: Predicting Optimization Selection for Stencil Computations across GPUs

StencilMART: Predicting Optimization Selection for Stencil C...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Qingxiao Sun Yi Liu Hailong Yang Zhonghui Jiang Zhongzhi Luan Depei Qian State Key Laboratory of Software Development Environment Beijing China School of Computer Science and Engineering Beihang University Beijing China

Stencil computations are widely used in high performance computing (HPC) applications. Many HPC platforms utilize the high computation capability of GPUs to accelerate stencil computations. In recent years, stencils have become more diverse in terms of stencil order, memory accesses and computation patterns. To adapt diverse stencils to GPUs, a variety of optimization techniques have been proposed such as streaming and retiming. However, due to the diversity of stencil patterns and GPU architectures, no single optimization technique fits all stencils. Besides, it is challenging to choose the most cost-efficient GPU for accelerating target stencils. To address the above problems, we propose StencilMART, an automatic optimization selection framework that predicts the best optimization combination and execution time under a certain parameter setting for stencils on GPUs. Specifically, the StencilMART represents the stencil patterns as binary tensors and neighboring features through tensor assignment and feature extraction. In addition, the StencilMART implements various machine learning methods such as classification and regression that utilize stencil representation and hardware characteristics for execution time prediction. The experiment results show that the StencilMART can achieve accurate optimization selection and performance prediction for various stencils across GPUs.

关键词： Distributed processing Tensors High performance computing Graphics processing units Machine learning computer architecture Feature extraction

来源：评论

学校读者我要写书评

暂无评论

GKT: A Novel Guidance-Based Knowledge Transfer Framework For Efficient Cloud-edge Collaboration LLM Deployment

arXiv

引用

arXiv 2024年

作者： Yao, Yao Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China

The burgeoning size of Large Language Models (LLMs) has led to enhanced capabilities in generating responses, albeit at the expense of increased inference times and elevated resource demands. Existing methods of acceleration, predominantly hinged on knowledge distillation, generally necessitate fine-tuning of considerably large models, posing a challenge for average users. Furthermore, present techniques for expediting inference and reducing costs operate independently. To address these issues, we introduce a novel and intuitive Guidance-based Knowledge Transfer (GKT) framework. This approach leverages a larger LLM as a "teacher" to create guidance prompts, paired with a smaller "student" model to finalize responses. Remarkably, GKT requires no fine-tuning and doesn’t necessitate the teacher and student models to have the same vocabulary, allowing for extensive batch generation to accelerate the process while ensuring user customization. GKT can be seamlessly integrated into cloud-edge collaboration architectures, and is versatile enough for plug-and-play application across various models. When utilizing ChatGPT as teacher model and Llama2-70B as the student model, we can achieve 95.00% of ChatGPT’s performance at 52% of the cost. The results highlight substantial enhancements in accuracy and processing speed on the GSM8K and CSQA datasets, surpassing the performance of using either the student or teacher models in isolation. Our code is publicly available at https://***/Zoeyyao27/GKT © 2024, CC BY.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Research on intelligent access control technology of face recognition model based on parameter sharing and dense connection

引用

International Journal of Computational Intelligence Studies 2023年第3-4期12卷 255-270页

作者： Xu, Yonghua School of Computer Engineering Jinling Institute of Technology Jiangsu Nanjing211169 China Jiangsu Key Laboratory of Data Science and Smart Software Jinling Institute of Technology Nanjing211169 China

This study proposes a laboratory intelligent facial recognition system based on improved CNN, which significantly improves the accuracy of facial recognition by optimising the portrait recognition algorithm, improving CNN calculation and large parameter scale, and utilising perspective projection to improve portrait effect and sample utilisation. The experimental results show that the recognition rate has been improved by 10%, the CPU usage rate is less than 100%, and the model parameters have been reduced by more than 95%. This system can effectively and accurately recognise faces, making it suitable for embedded facial recognition devices. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

engineering Assessment in the Age of Generative Artificial Intelligence: A Critical Analysis

Engineering Assessment in the Age of Generative Artificial I...

引用

World engineering Education Forum - Global engineering Deans Council (WEEF-GEDC)

作者： Scott Daniel Sasha Nikolic Carolyn Sandison Rezwanul Haque Sarah Grundy Marina Belkina Sarah Lyden Ghulam M. Hassan Peter Neal School of Professional Practice & Leadership University of Technology Sydney Sydney Australia Faculty of Engineering and Information Sciences University of Wollongong Wollongong Australia School of Science Technology and Engineering University of the Sunshine Coast Sippy Downs Australia School of Chemical Engineering University of New South Wales Sydney Australia College Western Sydney University Sydney Australia School of Engineering University of Tasmania Hobart Australia School of Computer Science & Software Engineering University of Western Australia Perth Australia School of Chemical Engineering University of New South Wales Australia Sydney Australia

ISBN: (数字)9798331519803

ISBN: (纸本)9798331519810

Generative Artificial Intelligence (GenAI) has significantly impacted higher education, offering numerous benefits alongside notable risks, particularly concerning academic integrity. This paper reviews the assessment landscape in the context of GenAI and critically analyses a key GenAI assessment framework against the latest assessment integrity research in engineering. Our analysis indicates that this framework presents a valuable opportunity for advancing engineering education.

关键词： Reviews Generative AI Learning (artificial intelligence) engineering education

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Traffic Trajectory Prediction via Spatial Attention Network for Internet of Vehicles

Heterogeneous Traffic Trajectory Prediction via Spatial Atte...

引用

International Conference on Big Data Computing and Communications (BIGCOM)

作者： Jie Li Yue Guo Han Shi Ruiyun Yu Xingwei Wang Xinyi Hou School of computer science and Engineering Northeastern University Shen Yang China Software College Northeastern University Shen Yang China

There are different types of traffic agents in urban scenes. Their movement behaviors influence each other. Accu-rately predicting trajectories of these traffic agents contributes to the advancement of autonomous driving technology. In recent years, deep learning technology has become a more popular method for extracting motion features. However, most of the studies cannot properly simulate the interaction between agents, which affects the performance of the algorithm. This paper proposes a heterogeneous traffic trajectory prediction algorithm based on spatial attention network. We combine the features of different types of agents to optimize the attention mechanism, so that the algorithm can adaptively extract the spatial relationship between them. In addition, we use LSTM to combine the interaction effects of traffic agents with their own movement patterns from both spatial and temporal perspectives. Finally, the future moving positon sequence of the agent is obtained. We use different datasets to evaluate the performance of the algorithm, and its prediction error is reduced by 15% compared with other methods.

关键词： Road transportation Deep learning Predictive models Big Data Prediction algorithms Feature extraction Trajectory

来源：评论

学校读者我要写书评

暂无评论

GICL: A Cross-Modal Drug Property Prediction Framework Based on Knowledge Enhancement of Large Language Models

引用

Journal of chemical information and modeling 2025年第11期65卷 2025 May 27页

作者： Na Li Jianbo Qiao Fei Gao Yanling Wang Hua Shi Zilong Zhang Feifei Cui Lichao Zhang Leyi Wei School of Computer and Information Engineering Qilu Institute of Technology Jinan 250200 China. School of Software Shandong University Jinan 250100 China. School of Optoelectronic and Communication Engineering Xiamen University of Technology Xiamen 361005 China. School of Computer Science and Technology Hainan University Haikou 570228 China. School of Intelligent Manufacturing and Equipment Shenzhen Institute of Information Technology Shenzhen 518172 China. Macao Polytechnic University Faculty of Applied Science Centre for Artificial Intelligence Driven Drug Discovery Macau 999078 China. Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR) Shandong University Jinan 250100 China.

Deep learning models have demonstrated their potential in learning effective molecular representations critical for drug property prediction and drug discovery. Despite significant advancements in leveraging multimodal drug molecule semantics, existing approaches often struggle with challenges such as low-quality data and structural complexity. Large language models (LLMs) excel in generating high-quality molecular representations due to their robust characterization capabilities. In this work, we introduce GICL, a cross-modal contrastive learning framework that integrates LLM-derived embeddings with molecular image representations. Specifically, LLMs extract feature representations from the SMILES strings of drug molecules, which are then contrasted with graphical representations of molecular images to achieve a holistic understanding of molecular features. Experimental results demonstrate that GICL achieves state-of-the-art performance on the ADMET task while offering interpretable insights into drug properties, thereby facilitating more efficient drug design and discovery.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

CTSSeg: Consistent Teacher-Student model for magnetic resonance image Segmentation

CTSSeg: Consistent Teacher-Student model for magnetic resona...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Chenbin Zhang Qingyuan He Kun Yan Meng Ma Defeng Liu Ping Wang School of Computer Science Peking University Beijing China Department of Radiology Peking University Third Hospital Beijing China School of Software and Microelectronics Peking University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China Center for Reproductive Medicine Peking University Third Hospital Beijing China School of Software and Microelectronics Peking University and the KeyLaboratory of High Confidence Software Technologies (PKU) Ministry of Education

Segmentation of magnetic resonance images is an essential way of measuring the volume of tissues and lesions, which can improve the efficiency of diagnosis. The mainstream image segmentation methods are based on deep learning, which requires a large amount of labeled data. However, labeling magnetic resonance images is expensive and time-consuming. Therefore, we propose a consistent teacher-student model for magnetic resonance image segmentation, which is abbreviated as CTSSeg. Specifically, the CTSSeg includes a student network and a teacher network, where the student network learns supervised from labeled data, while the teacher network utilizes unlabeled data to improve the student network via contrastive learning and pseudo-label learning. We evaluate the proposed CTSSeg on the Atrial Segmentation Challenge dataset and a local clinical dataset. The experimental results show that our method can make full use of both labeled and unlabeled data and yield state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantum reversible circuits for multiplicative inverse

引用

EPJ Quantum Technology 2022年第1期9卷 1-17页

作者： Luo, Qing-bin Yang, Guo-wu Li, Xiao-yu Li, Qiang Department of Computer Science and Technology School of Information Engineering Hubei Minzu University Enshi China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Big data research Center & School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu University of Information Technology Chengdu China

The synthesis of quantum circuits for multiplicative inverse over $\operatorname{GF}(2^{8})$ are discussed in this paper. We first convert the multiplicative inverse operation in $\operatorname{GF}(2^{8})$ to arithmetic operations in the composite field $\operatorname{GF}((2^{4})^{2})$ , and then discuss the expressions of the square calculation, the inversion calculation and the multiplication calculation separately in the finite field $\operatorname{GF}(2^{4})$ , where the expressions of multiplication calculation in $\operatorname{GF}(2^{4})$ are given directly in $\operatorname{GF}(2^{4})$ and given through being transformed into the composite field $\operatorname{GF}((2^{2})^{2})$ . Then the quantum circuits of these calculations are realized one by one. Finally, two quantum circuits for multiplicative inverse over $\operatorname{GF}(2^{8})$ are synthesized. They both use 21 qubits, the first quantum circuit uses 55 Toffoli gates and 107 CNOT gates and the second one uses 37 Toffoli gates and 209 CNOT gates. As an example of the application of multiplication inverse, we apply these quantum circuits to the implementations of the S-box quantum circuit of the AES cryptographic algorithm. Two quantum circuits for implementing the S-box of the AES cryptographic algorithm are presented. The first quantum circuit uses 21 qubits, 55 Toffoli gates, 131 CNOT gates and 4 NOT gates and the second one uses 21 qubits, 37 Toffoli gates, 233 CNOT gates and 4 NOT gates. Through the evaluation of quantum cost, the two quantum circuits of the S-box of AES cryptographic algorithm use less quantum resources than the existing schemes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A high robust and blind image watermarking using arnold transform mapping in the dct domain of ycbcr color space

Journal of Network Intelligence

引用

Journal of Network Intelligence 2021年第3期6卷 624-636页

作者： Lee, Chin-Feng Chang, Chin-Chen Wang, Zhi-Hui Di, Ya-Feng Department of Information Management Chaoyang University of Technology Taichung41349 Taiwan Department of Information Engineering and Computer Science Feng Chia University Taichung40224 Taiwan School of software Dalian University of Technology Dalian City Liaoning Province Dalian116620 China

This study proposes a robust and blind watermarking scheme, based on Arnold transform and DCT in YCbCr color space. Before embedding the watermark, the host image is scrambled using Arnold transform, and then the scrambled RGB image is converted into YCbCr color space. To improve the security of the scheme, the watermark is encrypted with a private key. The encrypted watermark is then embedded into the channels of YCbCr by the proposed method, which has low computation complexity. Experimental results reveal that the proposed scheme not only has good perceptual quality after embedding watermark, but also has satisfactory performance of robustness. More importantly, we verify that embedding the watermark into different channels can resist different attacks. This study also develops an expanded scheme including a voting mech-anism, which improves the robustness compared with state-of-the-art methods. © 2021 Taiwan Ubiquitous Information.

关键词： Mapping

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：