检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Wang, Qizhou Liu, Feng Han, Bo Liu, Tongliang Gong, Chen Niu, Gang Zhou, Mingyuan Sugiyama, Masashi Department of Computer Science Hong Kong Baptist University Hong Kong DeSI Lab Australian Artificial Intelligence Institute University of Technology Sydney Australia TML Lab School of Computer Science Faculty of Engineering The University of Sydney Australia PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of MoE Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China McCombs School of Business The University of Texas at Austin United States Graduate School of Frontier Sciences The University of Tokyo Japan

Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more critical and given larger weights. However, existing methods measuring the closeness are not very reliable: they are discrete and can take only a few values, and they are path-dependent, i.e., they may change given the same start and end points with different attack paths. In this paper, we propose three types of probabilistic margin (PM), which are continuous and path-independent, for measuring the aforementioned closeness and reweighting adversarial data. Specifically, a PM is defined as the difference between two estimated class-posterior probabilities, e.g., such a probability of the true label minus the probability of the most confusing label given some natural data. Though different PMs capture different geometric properties, all three PMs share a negative correlation with the vulnerability of data: data with larger/smaller PMs are safer/riskier and should have smaller/larger weights. Experiments demonstrated that PMs are reliable and PM-based reweighting methods outperformed state-of-the-art counterparts. Copyright © 2021, The Authors. All rights reserved.

关键词： Probability

来源：评论

学校读者我要写书评

暂无评论

On ADMM in deep learning: convergence and saturation-avoidance

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2021年第1期22卷 9024-9090页

作者： Jinshan Zeng Shao-Bo Lin Yuan Yao Ding-Xuan Zhou School of Computer and Information Engineering Jiangxi Normal University Nanchang China and Liu Bie Ju Centre for Mathematical Sciences City University of Hong Kong Hong Kong and Department of Mathematics Hong Kong University of Science and Technology Hong Kong Center of Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University Xi'an China Department of Mathematics Hong Kong University of Science and Technology Hong Kong School of Data Science and Department of Mathematics City University of Hong Kong Hong Kong

In this paper, we develop an alternating direction method of multipliers (ADMM) for deep neural networks training with sigmoid-type activation functions (called sigmoid-ADMM pair), mainly motivated by the gradient-free nature of ADMM in avoiding the saturation of sigmoid-type activations and the advantages of deep neural networks with sigmoid-type activations (called deep sigmoid nets) over their rectified linear unit (ReLU) counterparts (called deep ReLU nets) in terms of approximation. In particular, we prove that the approximation capability of deep sigmoid nets is not worse than that of deep ReLU nets by showing that ReLU activation function can be well approximated by deep sigmoid nets with two hidden layers and finitely many free parameters but not vice-verse. We also establish the global convergence of the proposed ADMM for the nonlinearly constrained formulation of the deep sigmoid nets training from arbitrary initial points to a Karush-Kuhn-Tucker (KKT) point at a rate of order O(1/k). Besides sigmoid activation, such a convergence theorem holds for a general class of smooth activations. Compared with the widely used stochastic gradient descent (SGD) algorithm for the deep ReLU nets training (called ReLU-SGD pair), the proposed sigmoid-ADMM pair is practically stable with respect to the algorithmic hyperparameters including the learning rate, initial schemes and the pro-processing of the input data. Moreover, we find that to approximate and learn simple but important functions the proposed sigmoid-ADMM pair numerically outperforms the ReLU-SGD pair.

关键词： deep learning ADMM sigmoid global convergence saturation avoidance

来源：评论

学校读者我要写书评

暂无评论

Culture versus Policy: More Global Collaboration to Effectively Combat COVID-19

引用

The Innovation 2020年第2期1卷 15-16页

作者： Jianping Li Kun Guo Enrique Herrera Viedma Heesoek Lee Jiming Liu Ning Zhong Luiz Flavio Autran Monteiro Gomes Florin Gheorghe Filip Shu-Cherng Fang Mujgan SagirÖzdemir Xiaohui Liu Guoqing Lu Yong Shi School of Economics and Management University of Chinese Academy of SciencesBeijing 100190China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of SciencesBeijing 100190China Research Center on Fictitious Economy&Data Science Chinese Academy of SciencesBeijing 100190China Department of Computer Science and Artificial Intelligence E.T.S.de Ingenieria Informatica y de TelecomunicacionesUniversity of Granada18071 GranadaSpain Department of Information Management Korea Advanced Institute of Science and TechnologySeoul 207-43 Korea Department of Computer Science and HKBU-CSD&NIPD Joint Research Laboratory for Intelligent Disease Surveillance and Control Hong Kong Baptist UniversityHong KongChina Department of Life Science and Informatics Maebashi Institute of TechnologyMaebashi 371-0816Japan Ibmec University Center Av.Presidente Wilson118Office#111020030-020 Rio de JaneiroBrazil The Romanian Academy Bucharest010071Romania Industrial and Systems Engineering Department North Carolina State UniversityRaleighNC 27695USA Department of Industrial Engineering Eskisehir Osmangazi University26480 EskisehirTurkey Department of Computer Science Brunel University LondonLondonUB83PHUK Department of Biology and School of Interdisciplinary Informatics University of Nebraska at OmahaOmahaNE 68182USA College of Information Science and Technology University of Nebraska at OmahaOmahaNE 68182USA

The outbreak of COVID-19 seriously challenges every government with regard to capacity and management of public health systems facing the catastrophic *** and anti-epidemic policy do not necessarily conflict with each *** countries and governments should be more tolerant to each other in seeking cultural and political consensus to overcome this historically tragic pandemic together.

关键词： seeking overcome policy

来源：评论

学校读者我要写书评

暂无评论

CARDIOCARE: An integrated platform for the management of elderly multimorbid patients with breast cancer therapy induced cardiac toxicity

CARDIOCARE: An integrated platform for the management of eld...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： G. Karanasiou L. Koumakis S. Sfakianakis G. Manikis G. Kalliatakis A. Antoniades L. Lakkas D. Mauri C. Cipolla K. Mazzocco A. Papakonstantinou G. Filippatos A. Constantinidou B. Šeruga C. Conti A. Bucur E. Pacella K. Marias M. Tsiknakis D.I. Fotiadis Unit of Medical Technology and Intelligent Information Systems University of Ioannina Ioannina Greece Foundation for Research and Technology - Hellas Institute of Computer Science Heraklion Crete Greece Computational Bio-Medicine Laboratory Institute of Computer Science Foundation for Research and Technology – Hellas Heraklion Greece Stremble Ventures Ltd Limassol Cyprus 2nd Department of Cardiology School of Medicine University of Ioannina Department of Medical Oncology University of Ioannina Greece Cardiology Division European Institute of Oncology Milan Italy Department for Breast Cancer Endocrine Tumors and Sarcoma Theme Cancer Karolinska University Hospital and the Department of Oncology-Pathology Karolinska Institute Stockholm Sweden Department of Cardiology National and Kapodistrian University of Athens School of Medicine Attikon University Hospital Athens Greece Bank of Cyprus Oncology Centre Bank of Cyprus Oncology Centre Nicosia Cyprus Department of Medical Oncology Institute of Oncology Ljubljana Ljubljana Slovenia Istituto di Management Sanitario S.r.l Milano Italy Philips Research Europe Eindhoven Netherlands European Society of Cardiology Brussels Belgium Department of Electrical and Computer Engineering Hellenic Mediterranean University Heraklion Crete Greece Medical Technology and Intelligent Information Systems University of Ioannina Ioannina Greece Biomedical Research Institute Foundation for Research and Technology – Hellas University Campus of Ioannina Greece

Breast cancer (BC) remains the most diagnosed cancer in women, accounting for 12% of new annual cancer cases in Europe and worldwide. Advances in surgery, radiotherapy and systemic treatment have resulted in improved clinical outcomes and increased survival rates in recent years. However, BC therapy-related cardiotoxicity, may severely impact short- and long-term quality of life and survival. This study presents the CARDIOCARE platform and its main components, which by integrating patient-specific data from different categories, data from patient-oriented eHealth applications and wearable devices, and by employing advanced data mining and machine learning approaches, provides the healthcare professionals with a valuable tool for effectively managing BC patients and preventing or alleviating treatment induced *** Relevance— Through the adoption of CARDIOCARE platform healthcare professionals are able to stratify patients for their risk for cardiotoxicity and timely apply adequate interventions to prevent its onset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

QA-KGNet: A Language Model-Driven knowledge Graph Question-Answering Model

引用

Ruan Jian Xue Bao/Journal of Software 2023年第10期34卷

作者： Qiao, Shao-Jie Yang, Guo-Ping Yu, Yong Han, Nan Qin, Xiao Qu, Lu-Lu Ran, Li-Qiong Li, He School of Software Engineering Chengdu University of Information Technology Chengdu610225 China Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music Chengdu610021 China School of Management Chengdu University of Information Technology Chengdu610225 China Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning530100 China School of Computer Science and Technology XiDian University Xi’an710071 China

The question-answering system based on knowledge graphs can analyze user questions, and has become an effective way to retrieve relevant knowledge and automatically answer the given questions. The knowledge graph-based question-answering system usually uses a neural program induction model to convert natural language question into a logical form, and the answer can be obtained by executing the logical form on the knowledge graph. However, the knowledge question-answering system by using pre-trained language models and knowledge graphs involves two challenges: 1) given the QA (Question-answering) context, relevant knowledge needs to be identified from a large KG (knowledge Graph);2) we need to perform the joint reasoning on QA context and KG. Based on these challenges, a language model-driven knowledge graph question-answering model is proposed, which connects the QA context and KG to form a joint graph, and uses a language model to calculate the relevance of the given QA context nodes and KG nodes, and a multi-head graph attention network is employed to update the node representation. Extensive experiments on the CommonsenseQA, OpenBookQA and MedQA-USMLE real datasets are conducted to evaluate the performance of QA-KGNet and the experimental results show that QA-KGNet outperforms existing benchmark models and exhibits excellent structured reasoning capability. © 2023 Chinese Academy of sciences. All rights reserved.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment

Adaptive Fractional Dilated Convolution Network for Image Ae...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Qiuyu Chen Wei Zhang Ning Zhou Peng Lei Yi Xu Yu Zheng Jianping Fan Department of Computer Science UNC Charlotte Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Amazon Lab126 School of Cyber Engineering Xidian University

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

To leverage deep learning for image aesthetics assessment, one critical but unsolved issue is how to seamlessly incorporate the information of image aspect ratios to learn more robust models. In this paper, an adaptive fractional dilated convolution (AFDC), which is aspect-ratio-embedded, composition-preserving and parameter-free, is developed to tackle this issue natively in convolutional kernel level. Specifically, the fractional dilated kernel is adaptively constructed according to the image aspect ratios, where the interpolation of nearest two integer dilated kernels are used to cope with the misalignment of fractional sampling. Moreover, we provide a concise formulation for mini-batch training and utilize a grouping strategy to reduce computational overhead. As a result, it can be easily implemented by common deep learning libraries and plugged into popular CNN architectures in a computation-efficient manner. Our experimental results demonstrate that our proposed method achieves state-of-the-art performance on image aesthetics assessment over the AVA dataset.

关键词： Kernel Convolution Training Machine learning Interpolation Task analysis Libraries

来源：评论

学校读者我要写书评

暂无评论

Adaptive fractional dilated convolution network for image aesthetics assessment

arXiv

引用

arXiv 2020年

作者： Chen, Qiuyu Zhang, Wei Zhou, Ning Lei, Peng Xu, Yi Zheng, Yu Fan, Jianping Department of Computer Science UNC Charlotte Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Amazon Lab126 School of Cyber Engineering Xidian University

关键词： Aspect ratio

来源：评论

学校读者我要写书评

暂无评论

Probabilistic margins for instance reweighting in adversarial training 21

Probabilistic margins for instance reweighting in adversaria...

引用

Proceedings of the 35th International Conference on Neural information Processing Systems

作者： Qizhou Wang Feng Liu Bo Han Tongliang Liu Chen Gong Gang Niu Mingyuan Zhou Masashi Sugiyama Department of Computer Science Hong Kong Baptist University DeSI Lab Australian Artificial Intelligence Institute University of Technology Sydney TML Lab School of Computer Science Faculty of Engineering The University of Sydney PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of MoE and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology RIKEN Center for Advanced Intelligence Project (AIP) McCombs School of Business The University of Texas at Austin RIKEN Center for Advanced Intelligence Project (AIP) and Graduate School of Frontier Sciences The University of Tokyo

ISBN: (纸本)9781713845393

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review of Artificial Fish Swarm Algorithms: Recent Advances and Applications

arXiv

引用

arXiv 2020年

作者： Pourpanah, Farhad Wang, Ran Lim, Chee Peng Wang, Xi-Zhao Yazdani, Danial College of Mathematics and Statistics Guangdong Key Lab. of Intelligent Information Processing Shenzhen University China Department of Electrical and Computer Engineering University of Windsor Canada College of Mathematics and Statistics Shenzhen Key Lab. of Advanced Machine Learning and Applications Guangdong Key Lab. of Intelligent Information Processing Shenzhen University China Institute for Intelligent Systems Research and Innovation Deakin University Australia College of Computer Science and Software Engineering Guangdong Key Lab. of Intelligent Information Processing Shenzhen University China School of Computer Science and Engineering Southern University of Science and Technology China

The Artificial Fish Swarm Algorithm (AFSA) is inspired by the ecological behaviors of fish schooling in nature, viz., the preying, swarming and following behaviors. Owing to a number of salient properties, which include flexibility, fast convergence, and insensitivity to the initial parameter settings, the family of AFSA has emerged as an effective Swarm Intelligence (SI) methodology that has been widely applied to solve real-world optimization problems. Since its introduction in 2002, many improved and hybrid AFSA models have been developed to tackle continuous, binary, and combinatorial optimization problems. This paper aims to present a concise review of the continuous AFSA, encompassing the original ASFA, its improvements and hybrid models, as well as their associated applications. We focus on articles published in high-quality journals since 2013. Our review provides insights into AFSA parameters modifications, procedure and sub-functions. The main reasons for these enhancements and the comparison results with other hybrid methods are discussed. In addition, hybrid, multi-objective and dynamic AFSA models that have been proposed to solve continuous optimization problems are elucidated. We also analyse possible AFSA enhancements and highlight future research directions for advancing AFSA-based models. Copyright © 2020, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Efficient 3D Deep LiDAR Odometry

arXiv

引用

arXiv 2021年

作者： Wang, Guangming Wu, Xinrui Jiang, Shuyang Liu, Zhe Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Key Laboratory of Artificial Intelligence of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China

An efficient 3D point cloud learning architecture, named EfficientLO-Net, for LiDAR odometry is first proposed in this paper. In this architecture, the projection-aware representation of the 3D point cloud is proposed to organize the raw 3D point cloud into an ordered data form to achieve efficiency. The Pyramid, Warping, and Cost volume (PWC) structure for the LiDAR odometry task is built to estimate and refine the pose in a coarse-to-fine approach. A projection-aware attentive cost volume is built to directly associate two discrete point clouds and obtain embedding motion patterns. Then, a trainable embedding mask is proposed to weigh the local motion patterns to regress the overall pose and filter outlier points. The trainable pose warp-refinement module is iteratively used with embedding mask optimized hierarchically to make the pose estimation more robust for outliers. The entire architecture is holistically optimized end-to-end to achieve adaptive learning of cost volume and mask, and all operations involving point cloud sampling and grouping are accelerated by projection-aware 3D feature learning methods. The superior performance and effectiveness of our LiDAR odometry architecture are demonstrated on KITTI, M2DGR, and Argoverse datasets. Our method outperforms all recent learning-based methods and even the geometry-based approach, LOAM with mapping optimization, on most sequences of KITTI odometry dataset. We open sourced our codes at: https://***/IRMVlab/EfficientLO-Net. Copyright © 2021, The Authors. All rights reserved.

关键词： Iterative methods

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：