检索结果-内蒙古大学图书馆

Anchor-based nearest class mean loss for convolutional neural networks

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Hao, Fusheng Cheng, Jun Wang, Lei Wang, Xinchao Cao, Jianzhong Hu, Xiping Tao, Dapeng Xi'an Institute of Optics and Precision Mechanics CAS China University of Chinese Academy of Sciences Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology CAS Department of Computer Science Stevens Insititute of Technology

Discriminative features are critical for machine learning applications. Most existing deep learning approaches, however, rely on convolutional neural networks (CNNs) for learning features, whose discriminant power is not explicitly enforced. In this paper, we propose a novel approach to train deep CNNs by imposing the intra-class compactness and the inter-class separability, so as to enhance the learned features' discriminant power. To this end, we introduce anchors, which are predefined vectors regarded as the centers for each class and fixed during training. Discriminative features are obtained by constraining the deep CNNs to map training samples to the corresponding anchors as close as possible. We propose two principles to select the anchors, and measure the proximity of two points using the Euclidean and cosine distance metric functions, which results in two novel loss functions. These loss functions require no sample pairs or triplets and can be efficiently optimized by batch stochastic gradient descent. We test the proposed method on three benchmark image classification datasets and demonstrate its promising results. Copyright © 2018, The Authors. All rights reserved.

关键词： Anchors

A full end-to-end semantic role labeler, syntax-agnostic over syntax-aware?

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Cai, Jiaxun He, Shexia Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction Cognitive Engineering Shanghai Jiao Tong University Shanghai China

Semantic role labeling (SRL) is to recognize the predicate-argument structure of a sentence, including subtasks of predicate disambiguation and argument labeling. Previous studies usually formulate the entire SRL problem into two or more subtasks. For the first time, this paper introduces an end-to-end neural model which unifiedly tackles the predicate disambiguation and the argument labeling in one shot. Using a biaffine scorer, our model directly predicts all semantic role labels for all given word pairs in the sentence without relying on any syntactic parse information. Specifically, we augment the BiLSTM encoder with a non-linear transformation to further distinguish the predicate and the argument in a given sentence, and model the semantic role labeling process as a word pair classification task by employing the biaffine attentional mechanism. Though the proposed model is syntax-agnostic with local decoder, it outperforms the state-of-the-art syntax-aware SRL systems on the CoNLL-2008, 2009 benchmarks for both English and Chinese. To our best knowledge, we report the first syntax-agnostic SRL model that surpasses all known syntax-aware models. Copyright © 2018, The Authors. All rights reserved.

关键词： Syntactics

Effective character-augmented word embedding for machine reading comprehension

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhang, Zhuosheng Huang, Yafang Zhu, Pengfei Zhao, Hai 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 Shanghai200240 China School of Computer Science and Software Engineering East China Normal University China

Machine reading comprehension is a task to model relationship between passage and query. In terms of deep learning framework, most of state-of-the-art models simply concatenate word and character level representations, which has been shown suboptimal for the concerned task. In this paper, we empirically explore different integration strategies of word and character embeddings and propose a character-augmented reader which attends character-level representation to augment word embedding with a short list to improve word representations, especially for rare words. Experimental results show that the proposed approach helps the baseline model significantly outperform state-of-the-art baselines on various public benchmarks. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

An Early Stage Researcher's Primer on Systems Medicine Terminology

学校读者我要写书评

暂无评论

Network and Systems Medicine

Network and Systems Medicine 2021年第1期4卷 2-50页

作者： Zanin, Massimiliano Aitya, Nadim A.A. Basilio, José Baumbach, Jan Benis, Arriel Behera, Chandan K. Bucholc, Magda Castiglione, Filippo Chouvarda, Ioanna Comte, Blandine Dao, Tien-Tuan Ding, Xuemei Pujos-Guillot, Estelle Filipovic, Nenad Finn, David P. Glass, David H. Harel, Nissim Iesmantas, Tomas Ivanoska, Ilinka Joshi, Alok Boudjeltia, Karim Zouaoui Kaoui, Badr Kaur, Daman Maguire, Liam P. McClean, Paula L. McCombe, Niamh De Miranda, João Luís Moisescu, Mihnea Alexandru Pappalardo, Francesco Polster, Annikka Prasad, Girijesh Rozman, Damjana Sacala, Ioan Sanchez-Bornot, Jose M. Schmid, Johannes A. Sharp, Trevor Solé-Casals, Jordi Spiwok, Vojtěch Spyrou, George M. Stalidzans, Egils Stres, Blaa Sustersic, Tijana Symeonidis, Ioannis Tieri, Paolo Todd, Stephen Van Steen, Kristel Veneva, Milena Wang, Da-Hui Wang, Haiying Wang, Hui Watterson, Steven Wong-Lin, Kongfatt Yang, Su Zou, Xin Schmidt, Harald H.H.W. Centro de Tecnología Biomédica Universidad Politécnica de Madrid Madrid Spain Intelligent Systems Research Centre School of Computing Engineering and Intelligent Systems Ulster University Ulster United Kingdom Center for Physiology and Pharmacology Institute of Vascular Biology and Thrombosis Research Medical University of Vienna Vienna Austria TUM School of Life Sciences Weihenstephan Technical University of Munich Freising Germany Holon Israel CNR National Research Council IAC Institute for Applied Computing Rome Italy Lab of Computing Medical Informatics and Biomedical Imaging Technologies School of Medicine Aristotle University of Thessaloniki Thessaloniki Greece Université Clermont Auvergne INRAE UNH Plateforme d'Exploration du Métabolisme MetaboHUB Clermont Clermont-Ferrand France Université de Technologie de Compiègne Compiègne France Labex MS2T Control of Technological Systems-of-Systems CNRS and Université de Technologie de Compiègne Compiègne France Faculty of Engineering University of Kragujevac Kragujevac Serbia Kragujevac Serbia Steinbeis Advanced Risk Technologies Institute Doo Kragujevac Kragujevac Serbia Pharmacology and Therapeutics School of Medicine Galway Neuroscience Centre National University of Ireland Galway Ireland School of Computing Ulster University Ulster United Kingdom Holon Israel Department of Mathematics and Natural Sciences Kaunas University of Technology Kaunas Lithuania Faculty of Computer Science and Engineering Ss. Cyril and Methodius University Skopje Macedonia Medicine Faculty Université Libre de Bruxelles CHU de Charleroi Charleroi Belgium Northern Ireland Centre for Stratified Medicine Biomedical Sciences Research Institute Ulster University Ulster United Kingdom Escola Superior de Tecnologia e Gestão Instituto Politécnico de Portalegre Portalegre Portugal Instituto Superior Técnico Universidade de Lisboa Lisboa Portugal Faculty of Automatic Control and Computers University Politehnica of B

Background: Systems Medicine is a novel approach to medicine, that is, an interdisciplinary field that considers the human body as a system, composed of multiple parts and of complex relationships at multiple levels, and further integrated into an environment. Exploring Systems Medicine implies understanding and combining concepts coming from diametral different fields, including medicine, biology, statistics, modeling and simulation, and data science. Such heterogeneity leads to semantic issues, which may slow down implementation and fruitful interaction between these highly diverse fields. Methods: In this review, we collect and explain more than100 terms related to Systems Medicine. These include both modeling and data science terms and basic systems medicine terms, along with some synthetic definitions, examples of applications, and lists of relevant references. Results: This glossary aims at being a first aid kit for the Systems Medicine researcher facing an unfamiliar term, where he/she can get a first understanding of them, and, more importantly, examples and references for digging into the topic. © Massimiliano Zanin et al., 2021;Published by Mary Ann Liebert, Inc. 2021.

关键词： Semantics

Investigating the sources of variable impact of pathogenic variants in monogenic metabolic conditions

学校读者我要写书评

暂无评论

Nature Communications 2025年第1期16卷 1-13页

作者： Wei, Angela Border, Richard Fu, Boyang Cullina, Sinéad Brandes, Nadav Jang, Seon-Kyeong Sankararaman, Sriram Kenny, Eimear E. Udler, Miriam S. Ntranos, Vasilis Zaitlen, Noah Arboleda, Valerie A. Interdepartmental Bioinformatics Program UCLA Los Angeles CA United States Department of Pathology and Laboratory Medicine David Geffen School of Medicine UCLA Los Angeles CA United States Department of Computational Medicine David Geffen School of Medicine UCLA Los Angeles CA United States Department of Human Genetics David Geffen School of Medicine UCLA Los Angeles CA United States Department of Computer Science UCLA Los Angeles CA United States Department of Neurology David Geffen School of Medicine UCLA Los Angeles CA United States Institute for Genomic Health Icahn School of Medicine at Mount Sinai New York NY United States Department of Genetics and Genomic Sciences Icahn School of Medicine at Mount Sinai New York NY United States Department of Epidemiology & Biostatistics UCSF San Francisco CA United States Department of Bioengineering & Therapeutic Sciences (HIVE) UCSF San Francisco CA United States Bakar Computational Health Sciences Institute UCSF San Francisco CA United States Division of Genomic Medicine Department of Medicine Icahn School of Medicine at Mount Sinai New York NY United States Center for Translational Genomics Icahn School of Medicine at Mount Sinai New York NY United States Center for Genomic Medicine Massachusetts General Hospital Boston MA United States The Broad Institute Boston MA United States

Over three percent of people carry a dominant pathogenic variant, yet only a fraction of carriers develop disease. Disease phenotypes from carriers of variants in the same gene range from mild to severe. Here, we investigate underlying mechanisms for this heterogeneity: variable variant effect sizes, carrier polygenic backgrounds, and modulation of carrier effect by genetic background (marginal epistasis). We leveraged exomes and clinical phenotypes from the UK Biobank and the Mt. Sinai BioMe Biobank to identify carriers of pathogenic variants affecting cardiometabolic traits. We employed recently developed methods to study these cohorts, observing strong statistical support and clinical translational potential for all three mechanisms of variable carrier penetrance and disease severity. For example, scores from our recent model of variant pathogenicity were tightly correlated with phenotype amongst clinical variant carriers, they predicted effects of variants of unknown significance, and they distinguished gain- from loss-of-function variants. We also found that polygenic scores modify phenotypes amongst pathogenic carriers and that genetic background additionally alters the effects of pathogenic variants through interactions. © The Author(s) 2025.

关键词：

A molecular single-cell lung atlas of lethal COVID-19 (vol 595, pg 114, 2021)

学校读者我要写书评

暂无评论

NATURE 2021年第7882期598卷 E2-E2页

作者： Melms, Johannes C. Biermann, Jana Huang, Huachao Wang, Yiping Nair, Ajay Tagore, Somnath Katsyv, Igor Rendeiro, Andre F. Amin, Amit Dipak Schapiro, Denis Frangieh, Chris J. Luoma, Adrienne M. Filliol, Aveline Fang, Yinshan Ravichandran, Hiranmayi Clausi, Mariano G. Alba, George A. Rogava, Meri Chen, Sean W. Ho, Patricia Montoro, Daniel T. Kornberg, Adam E. Han, Arnold S. Bakhoum, Mathieu F. Anandasabapathy, Niroshana Suarez-Farinas, Mayte Bakhoum, Samuel F. Bram, Yaron Borczuk, Alain Guo, Xinzheng V. Lefkowitch, Jay H. Marboe, Charles Lagana, Stephen M. Del Portillo, Armando Tsai, Emily J. Zorn, Emmanuel Markowitz, Glen S. Schwabe, Robert F. Schwartz, Robert E. Elemento, Olivier Saqi, Anjali Hibshoosh, Hanina Que, Jianwen Izar, Benjamin Department of Medicine Division of Hematology/Oncology Columbia University Irving Medical Center New York NY USA Columbia Center for Translational Immunology Columbia University Irving Medical Center New York NY USA Herbert Irving Comprehensive Cancer Center Columbia University Irving Medical Center New York NY USA Program for Mathematical Genomics Columbia University New York NY USA Columbia Center for Human Development Columbia University Irving Medical Center New York NY USA Division of Digestive and Liver Diseases Columbia University Irving Medical Center New York NY USA Department of Medicine Columbia University Irving Medical Center New York NY USA Institute of Human Nutrition Columbia University New York NY USA Department of Systems Biology Columbia University Irving Medical Center New York NY USA Department of Pathology and Cell Biology Columbia University Irving Medical Center New York NY USA Institute for Computational Biomedicine Weill Cornell Medicine New York NY USA Caryl and Israel Englander Institute for Precision Medicine Weill Cornell Medicine New York NY USA WorldQuant Initiative for Quantitative Prediction Weill Cornell Medicine New York NY USA Department of Physiology and Biophysics Weill Cornell Medical College New York NY USA Department of Dermatology Weill Cornell Medical College New York NY USA Meyer Cancer Center Weill Cornell Medical College New York NY USA Laboratory of Systems Pharmacology Harvard Medical School Boston MA USA Klarman Cell Observatory Broad Institute of MIT and Harvard Cambridge MA USA Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA USA Department of Cancer Immunology and Virology Dana-Farber Cancer Center Boston MA USA Human Immune Monitoring Core Columbia University Irving Medical Center New York NY USA Department of Medicine Division of Pulmonary and Critical Care Massachusetts General Hospital Boston MA USA Cell Circu

Fast neural chinese word segmentation for long sentences

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Duan, Sufeng Li, Jiangtong Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China

Rapidly developed neural models have achieved competitive performance in Chinese word segmentation (CWS) as their traditional counterparts. However, most of methods encounter the computational inefficiency especially for long sentences because of the increasing model complexity and slower decoders. This paper presents a simple neural segmenter which directly labels the gap existence between adjacent characters to alleviate the existing drawback. Our segmenter is fully endto-end and capable of performing segmentation very fast. We also show a performance difference with different tag sets. The experiments show that our segmenter can provide comparable performance with state-of-the-art. Copyright © 2018, The Authors. All rights reserved.

关键词： Computational linguistics

Open vocabulary learning for neural Chinese pinyin IME

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhang, Zhuosheng Huang, Yafang Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. Shanghai Jiao Tong University Shanghai China

Pinyin-to-character (P2C) conversion is the core component of pinyin-based Chinese input method engine (IME). However, the conversion is seriously compromised by the ambiguities of Chinese characters corresponding to pinyin as well as the predefined fixed vocabularies. To alleviate such inconveniences, we propose a neural P2C conversion model augmented by an online updated vocabulary with a sampling mechanism to support open vocabulary learning during IME working. Our experiments show that the proposed method outperforms commercial IMEs and state-of-theart traditional models on standard corpus and true inputting history dataset in terms of multiple metrics and thus the online updated vocabulary indeed helps our IME effectively follows user inputting behavior. Copyright © 2018, The Authors. All rights reserved.

关键词： Behavioral research

I know what you want: Semantic learning for text comprehension

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhang, Zhuosheng Wu, Yuwei Li, Zuchao He, Shexia Zhao, Hai 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 Shanghai200240 China

Who did what to whom is a major focus in natural language understanding, which is right the aim of semantic role labeling (SRL). Although SRL is naturally essential to text comprehension tasks, it is surprisingly ignored in previous work. This paper thus makes the first attempt to let SRL enhance text comprehension and inference through specifying verbal arguments and their corresponding semantic roles. In terms of deep learning models, our embeddings are enhanced by semantic role labels for more fine-grained semantics. We show that the salient labels can be conveniently added to existing models and significantly improve deep learning models in challenging text comprehension tasks. Extensive experiments on benchmark machine reading comprehension and inference datasets verify that the proposed semantic learning helps our system reach new state-of-the-art. Copyright © 2018, The Authors. All rights reserved.

关键词： Semantics