检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Liu, Fenglin Yang, Bang You, Chenyu Wu, Xian Ge, Shen Liu, Zhangdaihong Sun, Xu Yang, Yang Clifton, David A. Department of Engineering Science University of Oxford United Kingdom School of ECE Peking University China Department of Electrical Engineering Yale University United States Tencent JARVIS Lab China Oxford-Suzhou Centre for Advanced Research China MOE Key Lab of Computational Linguistics School of Computer Science Peking University China School of Public Health Shanghai Jiao Tong University School of Medicine China

Language models (LMs), including large language models (such as ChatGPT), have the potential to assist clinicians in generating various clinical notes. However, LMs are prone to produce "hallucinations", i.e., generated content that is not aligned with facts and knowledge. In this paper, we propose the Re3Writer method with retrieval-augmented generation and knowledge-grounded reasoning to enable LMs to generate faithful clinical texts. We demonstrate the effectiveness of our method in generating patient discharge instructions. It requires the LMs not to only understand the patients’ long clinical documents, i.e., the health records during hospitalization, but also to generate critical instructional information provided both to carers and to the patient at the time of discharge. The proposed Re3Writer imitates the working patterns of physicians to first retrieve related working experience from historical instructions written by physicians, then reason related medical knowledge. Finally, it refines the retrieved working experience and reasoned medical knowledge to extract useful information, which is used to generate the discharge instructions for previously-unseen patients. Our experiments show that, using our method, the performance of five representative LMs can be substantially boosted across all metrics. Meanwhile, we show results from human evaluations to measure the effectiveness in terms of fluency, faithfulness, and comprehensiveness. © 2022, CC BY-NC-SA.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Dynamic resolution network

arXiv

引用

arXiv 2021年

作者： Zhu, Mingjian Han, Kai Wu, Enhua Zhang, Qiulin Nie, Ying Lan, Zhenzhong Wang, Yunhe Zhejiang University China Huawei Noah’s Ark Lab State Key Lab of Computer Science ISCAS & University of Chinese Academy of Sciences China School of Engineering Westlake University China Institute of Advanced Technology Westlake Institute for Advanced Study University of Macau China BUPT.

Deep convolutional neural networks (CNNs) are often of sophisticated design with numerous learnable parameters for the accuracy reason. To alleviate the expensive costs of deploying them on mobile devices, recent works have made huge efforts for excavating redundancy in pre-defined architectures. Nevertheless, the redundancy on the input resolution of modern CNNs has not been fully investigated, i.e., the resolution of input image is fixed. In this paper, we observe that the smallest resolution for accurately predicting the given image is different using the same neural network. To this end, we propose a novel dynamic-resolution network (DRNet) in which the input resolution is determined dynamically based on each input sample. Wherein, a resolution predictor with negligible computational costs is explored and optimized jointly with the desired network. Specifically, the predictor learns the smallest resolution that can retain and even exceed the original recognition accuracy for each image. During the inference, each input image will be resized to its predicted resolution for minimizing the overall computation burden. We then conduct extensive experiments on several benchmark networks and datasets. The results show that our DRNet can be embedded in any off-the-shelf network architecture to obtain a considerable reduction in computational complexity. For instance, DR-ResNet-50 achieves similar performance with an about 34% computation reduction, while gaining 1.4% accuracy increase with 10% computation reduction compared to the original ResNet-50 on ImageNet. Code will be available at https://***/mindspore/models/tree/master/research/cv/DRNet. Copyright © 2021, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Survey on Deep Face Restoration: From Non-blind to Blind and Beyond

arXiv

引用

arXiv 2023年

作者： Li, Wenjie Wang, Mei Zhang, Kai Li, Juncheng Li, Xiaoming Zhang, Yuhang Gao, Guangwei Deng, Weihong Lin, Chia-Wen The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China The Computer Vision Lab ETH Zürich Zürich Switzerland The School of Communication and Information Engineering Shanghai University Shanghai China The Nanyang Technological University Singapore The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China The Department of Electrical Engineering National Tsing Hua University Hsinchu Taiwan

Face restoration (FR) is a specialized field within image restoration that aims to recover low-quality (LQ) face images into high-quality (HQ) face images. Recent advances in deep learning technology have led to significant progress in FR methods. In this paper, we begin by examining the prevalent factors responsible for real-world LQ images and introduce degradation techniques used to synthesize LQ images. We also discuss notable benchmarks commonly utilized in the field. Next, we categorize FR methods based on different tasks and explain their evolution over time. Furthermore, we explore the various facial priors commonly utilized in the restoration process and discuss strategies to enhance their effectiveness. In the experimental section, we thoroughly evaluate the performance of state-of-the-art FR methods across various tasks using a unified benchmark. We analyze their performance from different perspectives. Finally, we discuss the challenges faced in the field of FR and propose potential directions for future advancements. The open-source repository corresponding to this work can be found at https://***/24wenjie-li/Awesome-Face-Restoration. Copyright © 2023, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

New Piggybacking Codes with Lower Repair Bandwidth for Any Single-Node Failure

New Piggybacking Codes with Lower Repair Bandwidth for Any S...

引用

IEEE International Symposium on Information Theory

作者： Hao Shi Hanxu Hou Yunghsiang S. Han Patrick P. C. Lee Zhengyi Jiang Zhongyi Huang Bo Bai School of Mathematics Jilin University Theory Lab Central Research Institute 2012 Labs Huawei Tech. Co. Ltd. Department of Computer Science and Engineering The Chinese University of Hong Kong Shenzhen Institute for Advanced Study UESTC Department of Mathematics Sciences Tsinghua University

ISBN: (数字)9781665421591

ISBN: (纸本)9781665421607

Piggybacking codes are an important class of array codes with small sub-packetization to achieve small repair bandwidth for single-node failures. In this paper, we propose new piggybacking codes such that the sub-packetization is equal to the number of parity nodes. Our piggybacking codes have an efficient repair method for any single-node failure, including both data nodes and parity nodes. We show that the proposed piggybacking codes have strictly less repair bandwidth for any single-node failure than that of the existing piggybacking codes, when the code rate is k/n = 0.8, 0.9 and the number of parity nodes ranges from 6 to 40.

关键词： Codes Bandwidth Maintenance engineering Arrays

来源：评论

学校读者我要写书评

暂无评论

MV-TON: Memory-based video virtual Try-On Network

arXiv

引用

arXiv 2021年

作者： Zhong, Xiaojing Wu, Zhonghua Tan, Taizhe Lin, Guosheng Wu, Qingyao School of Software Engineering South China University of Technology Guangzhou China S-Lab for Advanced Intelligence School of Computer Science and Engineering Nanyang Technological University Singapore School of Computers Guangdong University of Technology Guangzhou China

With the development of Generative Adversarial Network, image-based virtual try-on methods have made great progress. However, limited work has explored the task of video-based virtual try-on while it is important in real-world applications. Most existing video-based virtual try-on methods usually require clothing templates and they can only generate blurred and low-resolution results. To address these challenges, we propose a Memory-based Video virtual Try-On Network (MV-TON), which seamlessly transfers desired clothes to a target person without using any clothing templates and generates high-resolution realistic videos. Specifically, MV-TON consists of two modules: 1) a try-on module that transfers the desired clothes from model images to frame images by pose alignment and region-wise replacing of pixels;2) a memory refinement module that learns to embed the existing generated frames into the latent space as external memory for the following frame generation. Experimental results show the effectiveness of our method in the video virtual try-on task and its superiority over other existing methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Assisted Design of Al-Zn-Mg-Cu Alloys with Dramatically Enhanced Combination of Mechanical Strength and Plasticity

SSRN

引用

SSRN 2022年

作者： Juan, Yongfei Niu, Guoshuai Jiang, Haitao Yang, Jian Tang, Wenqi Liang, Enquan Yang, Yang Dai, Yongbing Zhang, Jiao Sun, Baode Shanghai Key Lab of Advanced High-Temperature Materials and Precision Forming State Key Lab of Metal Matrix Composites School of Materials Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Shanghai Aircraft Design and Research Institute Commercial Aircraft Corporation of China Shanghai201210 China Collaborative Innovation Center for Advanced Ship and Deep-sea Exploration Shanghai Jiao Tong University Shanghai200240 China

Materials development is stuck in vast untapped composition space and traditional trial-and-error methods, efficiently discovering novel alloys remains a significant challenge. Herein, we propose a machine learning-based alloy optimal property design system (OPDS) to facilitate the rational design of high-performance aluminum alloy. A database comprising element contents, heat treatment parameters, and material properties was preliminarily constructed. Notably, five knowledge-based material descriptors, including absolute electronegativity ( ), atomic size difference ( ), mixing enthalpy ( ), mixing entropy ( ), and valence electron concentration (VEC), were employed to enhance the model interpretability. After feature engineering, eight key features associated with the material properties were screened out. Subsequently, five ML algorithms, including Support Vector Regression (SVR), Random Forest (RF), eXtreme Gradient Boosting (XGB), Gaussian Process Regression (GPR), and Multilayer Perceptron (MLP), were respectively employed to construct the prediction models. More crucially, we employed the optimum search method, Particle Swarm Optimization (PSO), to boost the mining ability of OPDS;meanwhile, the multi-objective prediction for tensile strength, yield strength, and elongation was conducted by calculating the Pareto front. According to the compositions and heat treatment strategy predicted by OPDS, a novel Al-Zn-Mg-Cu alloy (OPDS-1) with the average properties of 834 MPa for UTS, 798 MPa for YS, and 7.2% for EL was successfully synthesized. Furthermore, the strengthening mechanisms in this alloy were established quantitatively, accounting for solid-solution, grain-boundary, dislocation, precipitation, and dispersoid strengthening contributions. The calculations confirmed that the precipitation strengthening ( 439 MPa) was most critical in the final strength increment, agreeing with the microstructure analysis. © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Two New Piggybacking Designs with Lower Repair Bandwidth

arXiv

引用

arXiv 2022年

作者： Jiang, Zhengyi Hou, Hanxu Han, Yunghsiang S. Lee, Patrick P.C. Bai, Bo Huang, Zhongyi The Department of Mathematics Sciences Tsinghua University China Theory Lab Central Research Institute Huawei Technology Co. Ltd 2012 Labs China The Shenzhen Institute for Advanced Study University of Electronic Science and Technology China The Department of Computer Science and Engineering The Chinese University Hong Kong

Piggybacking codes are a special class of MDS array codes that can achieve small repair bandwidth with small sub-packetization by first creating some instances of an (n, k) MDS code, such as a Reed-Solomon (RS) code, and then designing the piggyback function. In this paper, we propose a new piggybacking coding design which designs the piggyback function over some instances of both (n, k) MDS code and (n, k' MDS code, when k ≥ k'. We show that our new piggybacking design can significantly reduce the repair bandwidth for single-node failures. When k = k', we design a piggybacking code that is MDS code and we show that the designed code has lower repair bandwidth for single-node failures than all existing piggybacking codes when the number of parity node r = n − k ≥ 8 and the sub-packetization α Copyright © 2022, The Authors. All rights reserved.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Sliding Mode Control of the PUMA 560 Robot

Sliding Mode Control of the PUMA 560 Robot

引用

International Conference on Control, Automation and Diagnosis (ICCAD)

作者： Arezki Fekik Ahmad Taher Azar Mohamed Lamine Hamida Hakim Denoun Dyhia Kais Sabrina Mohand Saidi Amar Bousbaine Nashwa Ahmad Kamal Ammar K. Al Mhdawi Chakib Ben Njima Department of Electrical Engineering University Akli Mohand Oulhadj-Bouria Bouira Algeria Electrical Engineering Advanced Technology Laboratory (LATAGE) Algeria Automated Systems & Soft Computing Lab (ASSCL) Prince Sultan University Riyadh Saudi Arabia College of Computer & Information Sciences Prince Sultan University Riyadh Saudi Arabia Faculty of Computers and Artificial Intelligence Benha University Egypt Department of Electrical Engineering L2CSP Laboratory Mouloud Mammeri University Algeria University of Derby College of Science and Engineering UK Faculty of Engineering Cairo University Giza Egypt Edge Hill University U.K University of Sousse Tunisia

The purpose of this article is to present the application of the sliding mode control and investigate its effectiveness when applied to a three-dimensional robotic manipulator model. The analysis is based on the application of the sliding mode control law for the PUMA 560 model, three degrees of freedom, through the development of a dynamic simulation model. The simulation results show the effectiveness of this proposed method for the automation of industrial applications, such as assembly, machining (deburring, trimming), and surface tracking (polishing). This technique provides a useful insight into the advantages of using sliding mode control laws in robotics applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Black Phosphorus-Organic Framework-Derived Pei/Peg Nanohybrid Prepared by a One-Pot Method for a Wide Detection Range Co2 Gas Sensor

SSRN

引用

SSRN 2022年

作者： Liu, Lulu Sang, Shengbo Han, Dan Liu, Zhihua Han, Xiaomei Li, Donghui Chen, Yi Liu, Dongming Liu, Xiaoru Zhuo, Kai Cheng, Yongqiang Yang, Kun Shanxi Key Laboratory of Micro Nano Sensors & Artificial Intelligence Perception College of Information and Computer Taiyuan University of Technology Taiyuan030024 China Key Lab of Advanced Transducers and Intelligent Control System of the Ministry of Education Taiyuan University of Technology Taiyuan030024 China Key Laboratory of Interface Science and Engineering in Advanced Materials Taiyuan University of Technology Ministry of Education Taiyuan030024 China

In this paper, we report a hybrid PEI/PEG-BP sensor (composite material of black phosphorus-organic framework-derived PEI/PEG nanohybrid) prepared by a one-pot method, in which the existence of PEI/PEG onto BP was confirmed by SEM, EDS, XPS and UPS. The gas sensing properties of the PEI/PEG-BP sensor, including the sensor response, response/recovery times, repeatability, selectivity, and effects of humidity on the sensor, were studied by exposure to several CO 2 gas concentrations ranging from 200 ppm to 300,000 ppm at room temperature (25 ℃). The results show that the PEI/PEG-BP sensor had an extremely wide detection range, with lower and upper detection limits of 200 ppm and 160,000 ppm, respectively. The response of the PEI/PEG-BP sensor to 200 ppm, and 160,000 ppm CO 2 gas at room temperature ( RT ) was 4.48%, and 254.02%, respectively, showing fast response/recovery time, excellent repeatability and high selectivity. The gas-sensing properties of the PEI/PEG-BP sensor are better than BP, PEI, PEG, PEI-BP and PEG-BP sensors. The superior properties of the PEI/PEG-BP sensor can be attributed to the BP framework, porous structure, electron doping, and surface reactive groups such as -NH 2 and -OH. The PEI/PEG-BP sensor, with its excellent gas-sensing performance will help us to further explore the changes of CO 2 concentration in microbial growth systems, natural environments, industrial production and so on. © 2022, The Authors. All rights reserved.

关键词： Carbon dioxide

来源：评论

学校读者我要写书评

暂无评论

Structured probabilistic end-to-end learning from crowds 29

Structured probabilistic end-to-end learning from crowds

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Chen, Zhijun Wang, Huimin Sun, Hailong Chen, Pengpeng Han, Tao Liu, Xudong Yang, Jie SKLSDE Lab School of Computer Science and Engineering Beihang University China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China Web Information Systems Delft University of Technology Netherlands

ISBN: (纸本)9780999241165

End-to-end learning from crowds has recently been introduced as an EM-free approach to training deep neural networks directly from noisy crowdsourced annotations. It models the relationship between true labels and annotations with a specific type of neural layer, termed as the crowd layer, which can be trained using pure backpropagation. Parameters of the crowd layer, however, can hardly be interpreted as annotator reliability, as compared with the more principled probabilistic approach. The lack of probabilistic interpretation further prevents extensions of the approach to account for important factors of annotation processes, e.g., instance difficulty. This paper presents SpeeLFC, a structured probabilistic model that incorporates the constraints of probability axioms for parameters of the crowd layer, which allows to explicitly model annotator reliability while benefiting from the end-to-end training of neural networks. Moreover, we propose SpeeLFC-D, which further takes into account instance difficulty. Extensive validation on real-world datasets shows that our methods improve the state-of-the-art. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. 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

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：