检索结果-内蒙古大学图书馆

Modeling named entity embedding distribution into hypersphere

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Zhuosheng Tang, Bingjie Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China Computer Science Department Brown University RI United States

This work models named entity distribution from a way of visualizing topological structure of embedding space, so that we make an assumption that most, if not all, named entities (NEs) for a language tend to aggregate together to be accommodated by a specific hypersphere in embedding space. Thus we present a novel open definition for NE which alleviates the obvious drawback in previous closed NE definition with a limited NE dictionary. Then, we show two applications with introducing the proposed named entity hypersphere model. First, using a generative adversarial neural network to learn a transformation matrix of two embedding spaces, which results in a convenient determination of named entity distribution in the target language, indicating the potential of fast named entity discovery only using isomorphic relation between embedding spaces. Second, the named entity hypersphere model is directly integrated with various named entity recognition models over sentences to achieve state-of-theart results. Only assuming that embeddings are available, we show a prior knowledge free approach on effective named entity distribution depiction. Copyright © 2019, The Authors. All rights reserved.

关键词： Embeddings

学校读者我要写书评

暂无评论

Subword ELMo

arXiv 2019年

作者： Li, Jiangtong Zhao, Hai Li, Zuchao Bi, Wei Liu, Xiaojiang Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Tencent AI Lab Shenzhen China

Embedding from Language Models (ELMo) has shown to be effective for improving many natural language processing (NLP) tasks, and ELMo takes character information to compose word representation to train language models. However, the character is an insufficient and unnatural linguistic unit for word representation. Thus we introduce Embedding from Subword-aware Language Models (ESuLMo) which learns word representation from subwords using unsupervised segmentation over words. We show that ESuLMo can enhance four benchmark NLP tasks more effectively than ELMo, including syntactic dependency parsing, semantic role labeling, implicit discourse relation recognition and textual entailment, which brings a meaningful improvement over ELMo. Copyright © 2019, The Authors. All rights reserved.

关键词： Embeddings

The 2021 report of the Lancet Countdown on health and climate change: code red for a healthy future (vol 398, pg 1619, 2021)

学校读者我要写书评

暂无评论

LANCET 2021年第10317期398卷 2148-2148页

作者： Romanello, M. McGushin, A. Di Napoli, C. [a]Institute for Global Health University College London London UK [b]Institute for Sustainable Resources University College London London UK [c]UCL Energy Institute University College London London UK [d]Institute for Environmental Design and Engineering University College London London UK [e]Department of Geography University College London London UK [f]The Bartlett School of Sustainable Construction University College London London UK [g]Centre for Human Health and Performance University College London London UK [h]School of Agriculture Policy and Development University of Reading Reading UK [i]Department of Meteorology University of Reading Reading UK [j]The Walker Institute University of Reading Reading UK [k]Department of Health Sciences University of York York UK [l]Institute for Environment and Human Security United Nations University Bonn Germany [m]Centre on Climate Change and Planetary Health London School of Hygiene & Tropical Medicine London UK [n]Centre for Mathematical Modelling of Infectious Diseases London School of Hygiene & Tropical Medicine London UK [o]Department of Public Health Environments and Society London School of Hygiene & Tropical Medicine London UK [p]Department of Earth System Science Tsinghua University Beijing China [q]Department of Environment Climate Change and Health World Health Organization Geneva Switzerland [r]Institute for Environmental Sciences World Health Organization Geneva Switzerland [s]Centre for Climate Change and Social Transformations School of Psychology Cardiff University Cardiff UK [t]Yale Center on Climate Change and Health Yale University New Haven CT USA [u]School of Government University of Birmingham Birmingham UK [v]Economic analysis of Climate Impacts and Policy Centro Euro-Mediterraneo sui Cambiamenti Climatici Venice Italy [w]Natural Resources Institute University of Greenwich London UK [x]Department of Global Health University of Washington Seattle WA USA [y]Centre for He

Author Correction: Pretrainable geometric graph neural network for antibody affinity maturation

学校读者我要写书评

暂无评论

Nature communications 2024年第1期15卷 8675页

作者： Huiyu Cai Zuobai Zhang Mingkai Wang Bozitao Zhong Quanxiao Li Yuxuan Zhong Yanling Wu Tianlei Ying Jian Tang BioGeometry Beijing China. Mila-Québec AI Institute Montréal QC Canada. Department of Computer Science and Operations Research Université de Montréal Montréal QC Canada. Shanghai Engineering Research Center for Synthetic Immunology Fudan University Shanghai China. MOE/NHC/CAMS Key Laboratory of Medical Molecular Virology Shanghai Frontiers Science Center of Pathogenic Microorganisms and Infection Shanghai Institute of Infectious Disease and Biosecurity School of Basic Medical Sciences Fudan University Shanghai China. Shanghai Engineering Research Center for Synthetic Immunology Fudan University Shanghai China. yanlingwu@***. MOE/NHC/CAMS Key Laboratory of Medical Molecular Virology Shanghai Frontiers Science Center of Pathogenic Microorganisms and Infection Shanghai Institute of Infectious Disease and Biosecurity School of Basic Medical Sciences Fudan University Shanghai China. yanlingwu@***. Shanghai Engineering Research Center for Synthetic Immunology Fudan University Shanghai China. tlying@***. MOE/NHC/CAMS Key Laboratory of Medical Molecular Virology Shanghai Frontiers Science Center of Pathogenic Microorganisms and Infection Shanghai Institute of Infectious Disease and Biosecurity School of Basic Medical Sciences Fudan University Shanghai China. tlying@***. BioGeometry Beijing China. tangjian@***. Mila-Québec AI Institute Montréal QC Canada. tangjian@***. Department of Decision Sciences HEC Montréal Montréal QC Canada. tangjian@***.

ExTra: Transfer-guided exploration

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Santara, Anirban Ravindran, Balaraman Madan, Rishabh Mitra, Pabitra Department of Computer Science and Engineering IIT Kharagpur Kharagpur WB721302 Robert Bosch Centre for Data Science and AI IIT Madras ChennaiTN600036 Autonomous Ground Vehicle Research Group IIT Kharagpur KharagpurWB721302

In this work we present a novel approach for transfer-guided exploration in reinforcement learning that is inspired by the human tendency to leverage experiences from similar encounters in the past while navigating a new task. Given an optimal policy in a related task-environment, we show that its bisimulation distance from the current task-environment gives a lower bound on the optimal advantage of state-action pairs in the current task-environment. Transfer-guided Exploration (ExTra) samples actions from a Softmax distribution over these lower bounds. In this way, actions with potentially higher optimum advantage are sampled more frequently. In our experiments on gridworld environments, we demonstrate that given access to an optimal policy in a related task-environment, ExTra can outperform popular domain-specific exploration strategies viz. epsilon greedy, Model-Based Interval Estimation - Exploration Based (MBIE-EB), Pursuit and Boltzmann in terms of sample complexity and rate of convergence. We further show that ExTra is robust to choices of source task and shows a graceful degradation of performance as the dissimilarity of the source task increases. We also demonstrate that ExTra, when used alongside traditional exploration algorithms, improves their rate of convergence. Thus it is capable of complimenting the efficacy of traditional exploration algorithms. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement learning

Adaptive initialization method for K-means algorithm

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yang, Jie Wang, Yu-Kai Yao, Xin Lin, Chin-Teng Computational Intelligence and Brain Computer Interface Lab Centre for AI FEIT University of Technology Sydney Australia Shenzhen Key Laboratory of Computational Intelligence Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China CERCIA School of Computer Science University of Birmingham BirminghamB15 2TT United Kingdom

The K-means algorithm is a widely used clustering algorithm that offers simplicity and efficiency. However, the traditional K-means algorithm uses the random method to determine the initial cluster centers, which make clustering results prone to local optima and then result in worse clustering performance. Many initialization methods have been proposed, but none of them can dynamically adapt to datasets with various characteristics. In our previous research, an initialization method for K-means based on hybrid distance was proposed, and this algorithm can adapt to datasets with different characteristics. However, it has the following drawbacks: (a) When calculating density, the threshold cannot be uniquely determined, resulting in unstable results. (b) Heavily depending on adjusting the parameter, the parameter must be adjusted five times to obtain better clustering results. (c) The time complexity of the algorithm is quadratic, which is difficult to apply to large datasets. In the current paper, we proposed an adaptive initialization method for the K-means algorithm (aiMK) to improve our previous work. aiMK can not only adapt to datasets with various characteristics but also obtain better clustering results within two interactions. In addition, we then leverage random sampling in aiMK, which is named as aiMK-RS, to reduce the time complexity. aiMK-RS is easily applied to large and high-dimensional datasets. We compared aiMK and aiMK-RS with 10 different algorithms on 16 normal and six extra-large datasets. The experimental results show that aiMK and aiMK-RS outperform the current initialization methods and several well-known clustering algorithms. Furthermore, aiMK-RS can significantly reduce the complexity of applying it to extra-large datasets with high dimensions. The time complexity of aiMK-RS is O(n). Copyright © 2019, The Authors. All rights reserved.

关键词： K-means clustering

Multiscale PHATE Exploration of SARS-CoV-2 Data Reveals Multimodal Signatures of Disease

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Kuchroo, Manik Huang, Jessie Wong, Patrick Grenier, Jean-Christophe Shung, Dennis Tong, Alexander Lucas, Carolina Klein, Jon Burkhardt, Daniel B. Gigante, Scott Godavarthi, Abhinav Rieck, Bastian Israelow, Benjamin Simonov, Michael Mao, Tianyang Oh, Ji Eun Silva, Julio Takahashi, Takehiro Odio, Camila D. Casanovas-Massana, Arnau Fournier, John Farhadian, Shelli Dela Cruz, Charles S. Ko, Albert I. Hirn, Matthew J. Wilson, F. Perry Hussin, Julie Wolf, Guy Iwasaki, Akiko Krishnaswamy, Smita Department of Neuroscience Yale University New HavenCT United States Department of Computer Science Yale University New HavenCT United States Department of Immunobiology Yale University New HavenCT United States Montreal Heart Institute MontréalQC Canada Department of Medicine Yale University New HavenCT United States Department of Genetics Yale University New HavenCT United States Computational Biology Bioinformatics Program Yale University New HavenCT United States Department of Applied Mathematics Yale University New HavenCT United States Department of Biosystems Science and Engineering ETH Zurich Switzerland Department of Epidemiology of Microbial Diseases Yale School of Public Health New HavenCT United States Department of Medicine Section of Infectious Diseases Yale University School of Medicine New HavenCT United States Department of Medicine Section of Pulmonary and Critical Care Medicine Yale University School of Medicine New HavenCT United States Department of Computational Mathematics Science and Engineering Michigan State University East LansingMI United States Department of Mathematics Michigan State University East LansingMI United States Clinical and Translational Research Accelerator Department of Medicine Yale University New HavenCT United States Faculty of Medicine Université de Montréal Québec Canada Mila – Quebec AI institute MontréalQC Canada Department of Mathematics and Statistics Université de Montréal MontréalQC Canada Howard Hughes Medical Institute Chevy ChaseMD United States

The biomedical community is producing increasingly high dimensional datasets, integrated from hundreds of patient samples, which current computational techniques struggle to explore. To uncover biological meaning from these complex datasets, we present an approach called Multiscale PHATE, which learns abstracted biological features from data that can be directly predictive of disease. Built on a coarse graining process called diffusion condensation, Multiscale PHATE learns a data topology that can be analyzed at coarse levels for high level summarizations of data, as well as at fine levels for detailed representations on subsets. We apply Multiscale PHATE to study the immune response to COVID-19 in 54 million cells from 168 hospitalized patients. Through our analysis of patient samples, we identify CD16hiCD66blo neutrophil and IFNγ+GranzymeB+ Th17 cell responses enriched in patients who die. Furthermore, we show that population groupings Multiscale PHATE discovers can be directly fed into a classifier to predict disease outcome. We also use Multiscale PHATE-derived features to construct two different manifolds of patients, one from abstracted flow cytometry features and another directly on patient clinical features, both associating immune subsets and clinical markers with outcome. © 2021, CC BY.

关键词： Coronavirus

Recognizing Disguised Faces in the Wild

学校读者我要写书评

暂无评论

IEEE Transactions on Biometrics, Behavior, and Identity Scie...

IEEE Transactions on Biometrics, Behavior, and Identity science 2019年第2期1卷 97-108页

作者： Maneet Singh Richa Singh Mayank Vatsa Nalini K. Ratha Rama Chellappa Department of Computer Science and Engineering IIIT Delhi New Delhi India IBM Research AI IBM T. J. Watson Research Center Yorktown Heights NY USA UMIACS University of Maryland at College Park College Park MD USA

Research in face recognition has seen tremendous growth over the past couple of decades. Beginning from algorithms capable of performing recognition in constrained environments, existing face recognition systems achieve very high accuracies on large-scale unconstrained face datasets. While upcoming algorithms continue to achieve improved performance, many of them are susceptible to reduced performance under disguise variations, one of the most challenging covariate of face recognition. In this paper, the disguised faces in the wild (DFW) dataset is presented, which contains over 11000 images of 1000 identities with variations across different types of disguise accessories (the DFW dataset link: http://***/resources/***). The images are collected from the Internet, resulting in unconstrained variations similar to real-world settings. This is a unique dataset that contains impersonator and genuine obfuscated face images for each subject. The DFW dataset has been analyzed in terms of three levels of difficulty: 1) easy; 2) medium; and 3) hard, in order to showcase the challenging nature of the problem. The dataset was released as part of the First International Workshop and Competition on DFW at the Conference on computer Vision and Pattern Recognition, 2018. This paper presents the DFW dataset in detail, including the evaluation protocols, baseline results, performance analysis of the submissions received as part of the competition, and three levels of difficulties of the DFW challenge dataset.

关键词： Face recognition Protocols Internet Conferences Authentication Task analysis

DAC: Data-free automatic acceleration of convolutional networks

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Li, Xin Zhang, Shuai Jiang, Bolan Qi, Yingyong Chuah, Mooi Choo Bi, Ning Qualcomm AI Research Department of Computer Science and Engineering Lehigh University

Deploying a deep learning model on mobile/IoT devices is a challenging task. The difficulty lies in the trade-off between computation speed and accuracy. A complex deep learning model with high accuracy runs slowly on resource-limited devices, while a light-weight model that runs much faster loses accuracy. In this paper, we propose a novel decomposition method, namely DAC, that is capable of factorizing an ordinary convolutional layer into two layers with much fewer parameters. DAC computes the corresponding weights for the newly generated layers directly from the weights of the original convolutional layer. Thus, no training (or fine-tuning) or any data is needed. The experimental results show that DAC reduces a large number of floating-point operations (FLOPs) while maintaining high accuracy of a pre-trained model. If 2% accuracy drop is acceptable, DAC saves 53% FLOPs of VGG16 image classification model on ImageNet dataset, 29% FLOPS of SSD300 object detection model on PASCAL VOC2007 dataset, and 46% FLOPS of a multi-person pose estimation model on Microsoft COCO dataset. Compared to other existing decomposition methods, DAC achieves better performance. Copyright © 2018, The Authors. All rights reserved.

关键词： Convolution