检索结果-内蒙古大学图书馆

CDOpt: A Python Package for a Class of Riemannian Optimization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xiao, Nachuan Hu, Xiaoyin Liu, Xin Toh, Kim-Chuan The Institute of Operations Research and Analytics National University of Singapore Singapore School of Computer and Computing Science Hangzhou City University Hangzhou China Academy of Edge Intelligence Hangzhou City University Gongshu Hangzhou China State Key Laboratory of Scientific and Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences University of Chinese Academy of Sciences China Department of Mathematics Institute of Operations Research and Analytics National University of Singapore Singapore

Optimization over an embedded submanifold defined by equality constraints c(x) = 0 has attracted much interest over the past few decades due to its wide applications in various areas, including computer vision, signal processing, numerical linear algebra, and deep learning. For solving such problems, many related optimization packages have been developed based on Riemannian optimization approaches, which rely on some basic geometrical materials of Riemannian manifolds, including Riemannian gradients, retractions, vector transports, etc. These geometrical materials can be challenging to determine in general. In fact, existing packages only accommodate a few well-known manifolds whose geometrical materials are more easily accessible. For other manifolds that are not contained in these packages, the users have to develop the geometric materials by themselves. In addition, it is not always tractable to adapt the advanced features from various state-of-the-art unconstrained optimization solvers to Riemannian optimization approaches. Here we introduce a user-friendly Python package, CDOpt (available at https: //***/ under BSD 3-clause license), for solving a class of Riemannian optimization problems. CDOpt is designed to complement existing Riemannian optimization packages by transforming Riemannian optimization problems into their unconstrained counterparts through the constraint dissolving approach. We prove that the when the penalty parameter in the constraint dissolving approach is sufficiently large, Riemannian optimization problems and their unconstrained counterparts are equivalent. Therefore, solving Riemannian optimization problems through CDOpt can directly benefit from various existing solvers and the rich expertise gained over the past few decades for unconstrained optimization. Moreover, all the computations in CDOpt related to any manifold in question are conducted through its constraints expression, hence users can easily define new manifolds in

关键词： Constrained optimization

SYNAPSE: An international roadmap to large brain imaging

学校读者我要写书评

暂无评论

Physics Reports 2023年第1期999卷 1-60页

作者： Stampfl, Anton P.J. Liu, Zhongdong Hu, Jun Sawada, Kei Takano, H. Kohmura, Yoshiki Ishikawa, Tetsuya Lim, Jae-Hong Je, Jung-Ho Low, Chian-Ming Teo, Alvin Tok, Eng Soon Tan, Tin Wee Ban, Kenneth Libedinsky, Camilo Tan, Francis Chee Kuan Chen, Kuan-Peng Yang, An-Cheng Chuang, Chao-Chun Chen, Nan-Yow Shih, Chi-Tin Lee, Ting-Kuo Yang, De-Nian Lai, Hsu-Chao Shuai, Hong-Han Cheng, Chang-Chieh Ching, Yu-Tai Li, Chia-Wei Charng, Ching-Che Lo, Chung-Chuan Chiang, Ann-Shyn Recur, Benoit Petibois, Cyril Cheng, Chia-Liang Chen, Hsiang-Hsin Yang, Shun-Min Hwu, Yeukuang Rojviriya, Catleya Rugmai, Supagorn Rujirawat, Saroj Margaritondo, Giorgio Australian Nuclear Science and Technology Organization Lucas Heights 2234 NSW Australia Henan university of Technology Zhengzhou China Shanghai Institute of Applied Physics Chinese Academy of Science Shanghai China RIKEN SPring-8 Center Hyogo 679-5148 Japan Pohang Accelerator Laboratory Pohang University of Science and Technology Pohang Gyeongbuk 37673 South Korea Department of Materials Science and Engineering Pohang University of Science and Technology Gyeongbuk Pohang 37673 South Korea Department of Pharmacology Department of Anaesthesia and Healthy Longevity Research Programme Yong Loo Lin School of Medicine National University of Singapore Singapore School of Chemical and Life Sciences Nanyang Polytechnic Singapore eMaGIC-Lab Department of Physics National University of Singapore Singapore National Supercomputing Center Singapore Department of Psychology The N1 Institute for Health National University of Singapore Singapore Institute of Molecular and Cell Biology A*STAR Singapore Department of Anaesthesia National University Hospital National University Health System Singapore National Center for High-Performance Computing Hsinchu Taiwan Department of Physics Tunghai University Taichung Taiwan Department of Physics National Tsing Hua University Hsinchu Taiwan Institute of Information Science Academia Sinica Taipei Taiwan Department of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Information Technology Service Center National Yang Ming Chiao Tung University Hsinchu Taiwan National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Life Science National Tsing Hua University Hsinchu Taiwan Institute of Systems Neuroscience and Brain Research Center National Tsing Hua University Hsinchu Taiwan Institute of Physics Academia Sinica Taipei Taiwan Department of Physics National Dong Hwa University

Since 2020, synchrotron radiation facilities in several Asia-Pacific countries have been collaborating in a major project called “SYNAPSE” (Synchrotrons for Neuroscience: an Asia-Pacific Scientific Enterprise). They use x-ray imaging to attack in a coordinated fashion one of the major issues in modern science: the structure of animal and human brains, including neurons and connections. The objective is to develop Google-like maps also including detailed structural and functional information for selected regions of interest. The sheer mass of data needed for the objective poses huge problems for the acquisition, processing, storage and use of images. In order to complete the task within a reasonable time, the key element of the SYNAPSE strategy is the parallel and coordinated work of several facilities on the same specimens. This article reviews different aspects of the enterprise, including the foundations of synchrotron radiation, coherence and of its role in advanced imaging, electron accelerators, x-ray optics and detectors. This will provide the foundation for an extensive presentation of the different components of SYNAPSE, with an overview of results already obtained within the consortium. © 2022

关键词： Brain mapping Phase contrast Radiology Supercomputing Synchrotron X-rays

Fuzzy Attention Neural Network to Tackle Discontinuity in Airway Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Nan, Yang Del Ser, Javier Tang, Zeyu Tang, Peng Xing, Xiaodan Fang, Yingying Herrera, Francisco Pedrycz, Witold Walsh, Simon Yang, Guang National Heart and Lung Institute Imperial College London London United Kingdom Department of Communications Engineering University of the Basque Country UPV/EHU Bilbao Spain Derio Spain Department of Informatics Technical University of Munich Germany University of Granada Granada Spain Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Department of Electrical and Computer Engineering Faculty of Engineering King Abgudulaziz University Jeddah Saudi Arabia The Systems Research Institute Polish Academy of Sciences Warsaw Poland Royal Brompton Hospital Sydney Street London United Kingdom

Airway segmentation is crucial for the examination, diagnosis, and prognosis of lung diseases, while its manual delineation is unduly burdensome. To alleviate this time-consuming and potentially subjective manual procedure, researchers have proposed methods to automatically segment airways from computerized tomography (CT) images. However, some small-sized airway branches (e.g., bronchus and terminal bronchioles) significantly aggravate the difficulty of automatic segmentation by machine learning models. In particular, the variance of voxel values and the severe data imbalance in airway branches make the computational module prone to discontinuous and false-negative predictions. especially for cohorts with different lung diseases. Attention mechanism has shown the capacity to segment complex structures, while fuzzy logic can reduce the uncertainty in feature representations. Therefore, the integration of deep attention networks and fuzzy theory, given by the fuzzy attention layer, should be an escalated solution for better generalization and robustness. This paper presents an efficient method for airway segmentation, comprising a novel fuzzy attention neural network and a comprehensive loss function to enhance the spatial continuity of airway segmentation. The deep fuzzy set is formulated by a set of voxels in the feature map and a learnable Gaussian membership function. Different from the existing attention mechanism, the proposed channel-specific fuzzy attention addresses the issue of heterogeneous features in different channels. Furthermore, a novel evaluation metric is proposed to assess both the continuity and completeness of airway structures. The efficiency, generalization and robustness of the proposed method have been proved by training on normal lung disease while testing on datasets of lung cancer, COVID-19 and pulmonary fibrosis. © 2022, CC BY-NC-ND.

关键词： COVID-19

Social Presence in Evaluations for a Humanoid Robot and Its Effect on Children-Robot Relationship 23rd

学校读者我要写书评

暂无评论

Social Presence in Evaluations for a Humanoid Robot and Its ...

23rd International Conference on Human-computer Interaction, HCII 2021

作者： Chen, Yi-Chen Gamborino, Edwinn Fu, Li-Chen Yueh, Hsiu-Ping Yeh, Su-Ling Department of Psychology National Taiwan University Taipei Taiwan Department of Electrical Engineering and Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan MOST Joint Research Center for AI Technology and All Vista Healthcare Taipei Taiwan Center for Artificial Intelligence and Advanced Robotics National Taiwan University Taipei Taiwan Department of Bio-Industry Communication and Development National Taiwan University Taipei Taiwan Graduate Institute of Brain and Mind Sciences National Taiwan University Taipei Taiwan

ISBN: (纸本)9783030786342

As children are at a critical stage in their lives in developing and practicing social skills, they tend to imagine objects as interactive agents. For example, even a toy dinosaur can be perceived as affable and more as a social entity, namely, with a strong social presence (SP). This study investigated whether perceived SP changes (measured using the SP questionnaire) as children interacted with a robot. Furthermore, we investigated how SP modulated children-robot relationships and children’s overall attitudes towards robots. Children aged 6–12 interacted with a companion robot, RoBoHoN, for short intervals. Attitude evaluations were completed at three-time points: prior-, mid-, and post-interaction. SP and rapport with RoBoHoN were measured and compared mid-and post-interaction, while attitudes towards the robot were tested prior- and post-interaction. The results showed a stronger intention to use robots before interaction correlated with higher SP scores with RoBoHoN. As SP level was stable across mid- and post-interaction, we analyzed SP as a between-groups factor to compare attitude evaluations among children who rated RoBoHoN with higher versus lower SP scores. The high SP group found RoBoHoN to be more likable and playing with it as more enjoyable, but the effect on rapport level was marginal. The Implicit Association Task revealed no bias towards robots among children in both groups. This study shows SP’s positive effect on children-robot interaction and highlights the importance of SP in designing social companion robots for children. © 2021, Springer Nature Switzerland AG.

关键词： Association reactions

DAGs with no curl: An efficient DAG structure learning approach

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yu, Yue Gao, Tian Yin, Naiyu Ji, Qiang Department of Mathematics Lehigh University BethlehemPA United States IBM Research Yorktown HeightsNY United States Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute TroyNY United States

Recently directed acyclic graph (DAG) structure learning is formulated as a constrained continuous optimization problem with continuous acyclicity constraints and was solved iteratively through subproblem optimization. To further improve efficiency, we propose a novel learning framework to model and learn the weighted adjacency matrices in the DAG space directly. Specifically, we first show that the set of weighted adjacency matrices of DAGs are equivalent to the set of weighted gradients of graph potential functions, and one may perform structure learning by searching in this equivalent set of DAGs. To instantiate this idea, we propose a new algorithm, DAG-NoCurl, which solves the optimization problem efficiently with a two-step procedure: 1) first we find an initial cyclic solution to the optimization problem, and 2) then we employ the Hodge decomposition of graphs and learn an acyclic graph by projecting the cyclic graph to the gradient of a potential function. Experimental studies on benchmark datasets demonstrate that our method provides comparable accuracy but better efficiency than baseline DAG structure learning methods on both linear and generalized structural equation models, often by more than one order of magnitude. © 2021, CC BY-NC-ND.

关键词： Directed graphs

Entity concept-enhanced few-shot relation extraction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yang, Shan Zhang, Yongfei Niu, Guanglin Zhao, Qinhua Pu, Shiliang Beijing Key Laboratory of Digital Media School of Computer Science and Engineering BeiHang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems BeiHang University Beijing100191 China Pengcheng Laboratory Shenzhen518055 China State Key Laboratory of Software Development Environment School of Computer Science and Engineering BeiHang University Beijing100191 China Hikvision Research Institute Hangzhou311500 China

Few-shot relation extraction (FSRE) is of great importance in long-tail distribution problem, especially in special domain with low-resource data. Most existing FSRE algorithms fail to accurately classify the relations merely based on the information of the sentences together with the recognized entity pairs, due to limited samples and lack of knowledge. To address this problem, in this paper, we proposed a novel entity CONCEPTenhanced FEw-shot Relation Extraction scheme (ConceptFERE), which introduces the inherent concepts of entities to provide clues for relation prediction and boost the relations classification performance. Firstly, a conceptsentence attention module is developed to select the most appropriate concept from multiple concepts of each entity by calculating the semantic similarity between sentences and concepts. Secondly, a self-attention based fusion module is presented to bridge the gap of concept embedding and sentence embedding from different semantic spaces. Extensive experiments on the FSRE benchmark dataset FewRel have demonstrated the effectiveness and the superiority of the proposed ConceptFERE scheme as compared to the state-of-the-art baselines. Code is available at https://***/LittleGuoKe/ConceptFERE. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

Modern deep learning in bioinformatics

学校读者我要写书评

暂无评论

Journal of Molecular Cell Biology 2020年第11期12卷 823-827页

作者： Haoyang Li Shuye Tian Yu Li Qiming Fang Renbo Tan Yijie Pan Chao Huang Ying Xu Xin Gao Cancer Systems Biology Center The China-Japan Union HospitalJilin UniversityChangchun 130033China MOE Key Laboratory of Symbolic Computation and Knowledge Engineering College of Computer Science and TechnologyJilin UniversityChangchun 130012China Department of Biology Southern University of Science and TechnologyShenzhen 518055China Computational Bioscience Research Center(CBRC) Computer Electrical and Mathematical Sciences and Engineering(CEMSE)DivisionKing Abdullah University of Science and Technology(KAUST)Thuwal 23955Saudi Arabia School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou 310018China Ningbo Institute of Information Technology Application Chinese Academy of SciencesNingbo 315040China Computational Systems Biology Lab Department of Biochemistry and Molecular Biology and Institute of BioinformaticsUniversity of GeorgiaAthensGA 30602USA

Deep learning(DL)has shown explosive growth in its application to bioinformatics and has demonstrated thrillingly promising power to mine the complex relationship hidden in large-scale biological and biomedical data.A number of comprehensive reviews have been published on such applications,ranging from high-level reviews with future perspectives to those mainly serving as tutorials.

关键词： has such she

Multispectral Vineyard Segmentation: A Deep Learning Comparison Study

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Barros, Tiago Conde, P. Gonçalves, G. Premebida, C. Monteiro, M. Ferreira, C.S.S. Nunes, U.J. University of Coimbra Institute of Systems and Robotics Department of Electrical and Computer Engineering Coimbra Portugal University of Coimbra Institute for Systems Engineering and Computers at Coimbra Department of Mathematics Coimbra Portugal Research Centre for Natural Resources Environment and Society Polytechnic Institute of Coimbra Coimbra Agrarian Technical School Coimbra Portugal Bolin Centre for Climate Research Department of Physical Geography Stockholm University Stockholm Sweden Navarino Environmental Observatory Navarino Dunes Messinia Greece

Digital agriculture has evolved significantly over the last few years due to the technological developments in automation and computational intelligence applied to the agricultural sector, including vineyards which are a relevant crop in the Mediterranean region. In this work, a study is presented of semantic segmentation for vine detection in real-world vineyards by exploring state-of-the-art deep segmentation networks and conventional unsupervised methods. Camera data have been collected on vineyards using an Unmanned Aerial System (UAS) equipped with a dual imaging sensor payload, namely a high-definition RGB camera and a five-band multispectral and thermal camera. Extensive experiments using deep-segmentation networks and unsupervised methods have been performed on multimodal datasets representing four distinct vineyards located in the central region of Portugal. The reported results indicate that SegNet, U-Net, and ModSegNet have equivalent overall performance in vine segmentation. The results also show that multimodality slightly improves the performance of vine segmentation, but the NIR spectrum alone generally is sufficient on most of the datasets. Furthermore, results suggest that high-definition RGB images produce equivalent or higher performance than any lower resolution multispectral band combination. Lastly, Deep Learning (DL) networks have higher overall performance than classical methods. The code and dataset are publicly available on https://***/Cybonic/***. © 2021, CC BY.

关键词： Precision agriculture

Mesh Saliency Detection Using Convolutional Neural Networks

学校读者我要写书评

暂无评论

Mesh Saliency Detection Using Convolutional Neural Networks

IEEE International Conference on Multimedia and Expo (ICME)

作者： Stavros Nousias Gerasimos Arvanitis Aris S. Lalos Konstantinos Moustakas Department of Electrical & Computer Engineering University of Patras Greece Athena Research Center Industrial Systems Institute Greece

ISBN: (数字)9781728113319

ISBN: (纸本)9781728113326

Mesh saliency has been widely considered as the measure of visual importance of certain parts of 3D geometries, distinguishable from their surroundings, with respect to human visual perception. This work is based on the use of convolutional neural networks to extract saliency maps for large and dense 3D scanned models. The network is trained with saliency maps extracted by fusing local and global spectral characteristics. Extensive evaluation studies carried out using various 3D models, include visual perception evaluation in simplification and compression use cases. As a result, they verify the superiority of our approach as compared to other state-of-the-art approaches. Furthermore, these studies indicate that CNN-based saliency extraction method is much faster in large and dense geometries, allowing the application of saliency aware compression and simplification schemes in low-latency and energy-efficient systems.

关键词： Three-dimensional displays Feature extraction Training Sparse matrices Visualization Matrix decomposition Geometry