检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Papamarkou, Theodore Skoularidou, Maria Palla, Konstantina Aitchison, Laurence Arbel, Julyan Dunson, David Filippone, Maurizio Fortuin, Vincent Hennig, Philipp Hernández-Lobato, José Miguel Hubin, Aliaksandr Immer, Alexander Karaletsos, Theofanis Khan, Mohammad Emtiyaz Kristiadi, Agustinus Li, Yingzhen Mandt, Stephan Nemeth, Christopher Osborne, Michael A. Rudner, Tim G.J. Rügamer, David Teh, Yee Whye Welling, Max Wilson, Andrew Gordon Zhang, Ruqi Department of Mathematics The University of Manchester Manchester United Kingdom Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge United States Spotify London United Kingdom Computational Neuroscience Unit University of Bristol Bristol United Kingdom Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University United States Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany Department of Computer Science Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge United Kingdom Department of Mathematics University of Oslo Oslo Norway Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative CA United States Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London United Kingdom Department of Computer Science UC Irvine Irvine United States Department of Mathematics and Statistics Lancaster University Lancaster United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Center for Data Science New York University New York United States Department of Statistics LMU Munich Munich Germany DeepMind London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences Center for Data Science Computer Science Department New York University New York United States Department of Computer Science Purdue University West Lafayette United States

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Structured time-delay models for dynamical systems with connections to Frenet-Serret frame

arXiv

引用

arXiv 2021年

作者： Hirsh, Seth M. Ichinaga, Sara M. Brunton, Steven L. Kutz, J. Nathan Brunton, Bingni W. Department of Physics University of Washington SeattleWA United States Applied and Computational Mathematical Sciences Program University of Washington SeattleWA United States Department of Mechanical Engineering University of Washington SeattleWA United States Department of Applied Mathematics University of Washington SeattleWA United States Department of Biology University of Washington SeattleWA United States

Time-delay embeddings and dimensionality reduction are powerful techniques for discovering effective coordinate systems to represent the dynamics of physical systems. Recently, it has been shown that models identified by dynamic mode decomposition (DMD) on time-delay coordinates provide linear representations of strongly nonlinear systems, in the so-called Hankel alternative view of Koopman (HAVOK) approach. Curiously, the resulting linear model has a matrix representation that is approximately antisymmetric and tridiagonal with a zero diagonal;for chaotic systems, there is an additional forcing term in the last component. In this paper, we establish a new theoretical connection between HAVOK and the Frenet-Serret frame from differential geometry, and also develop an improved algorithm to identify more stable and accurate models from less data. In particular, we show that the sub- and super-diagonal entries of the linear model correspond to the intrinsic curvatures in Frenet-Serret frame. Based on this connection, we modify the algorithm to promote this antisymmetric structure, even in the noisy, low-data limit. We demonstrate this improved modeling procedure on data from several nonlinear synthetic and real-world examples. © 2021, CC BY.

关键词： Time delay

来源：评论

学校读者我要写书评

暂无评论

Quantum machine learning-based electrokinetic mining for the identification of nanoparticles and exosomes with minimal training data

引用

Bioactive Materials 2025年 51卷 414-430页

作者： Thakur, Abhimanyu Santos Bezerra, Pedro Correia Abhishek Zeng, Shihao Zhang, Kui Treptow, Werner Luna, Alexander Dougherty, Urszula Kwesi, Akushika Huang, Isabella R. Bestvina, Christine Garassino, Marina Chiara Duan, Fuyu Gokhale, Yash Duan, Bin Chen, Yin Lian, Qizhou Bissonnette, Marc Huang, Jianpan Chen, Huanhuan Joyce Pritzker School of Molecular Engineering University of Chicago IL United States Ben May Department for Cancer Research University of Chicago IL United States The University of Chicago Booth School of Business Chicago IL United States Department of Analytics Northeastern University Boston MA United States Department of Diagnostic Radiology The University of Hong Kong 5 Sassoon Road Hong Kong Theoretical and Computational Biology Lab (LBTC) from Universidade de Brasília (UnB) Brazil Section of Gastroenterology Hepatology and Nutrition Department of Medicine The University of Chicago Chicago IL United States The Laboratory Schools The University of Chicago Chicago IL United States Department of Medicine Section of Hematology/Oncology The University of Chicago Chicago IL United States Department of Hematology/Oncology The University of Chicago Chicago IL United States Mary & Dick Holland Regenerative Medicine Program and Division of Cardiology Department of Internal Medicine University of Nebraska Medical Center Omaha NE United States Department of Pharmacology and Toxicology College of Pharmacy University of Arizona Tucson AZ United States Faculty of Synthetic Biology Shenzhen University of Advanced Technology Key Laboratory of Quantitative Synthetic Biology Shenzhen Institute of Synthetic Biology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Center for Translational Stem Cell Biology Hong Kong HKUMed Laboratory of Cellular Therapeutics University of Hong Kong 999077 Hong Kong Department of Surgery The University of Hong Kong Shenzhen Hospital Shenzhen 518053 China

Synthetic and naturally occurring particles, such as nanoparticles (NPs) and exosomes;a type of extracellular vesicles (EVs), have garnered widespread attention across various fields, including biomaterials, oncology, and delivery systems for drugs and vaccines. Traditional methods for identifying NPs and EVs, such as transmission electron microscopy, are often prohibitively expensive and labor-intensive. As an alternative, the assessment of electrokinetic attributes such as zeta potential or electrophoretic mobility, conductance, and mean count rate, offers a more cost-effective, rapid, and reliable means of characterizing these particles. In this context, we introduce the first application of a quantum machine learning (QML)-based electrokinetic mining for the identification of green-synthesized iron- and cobalt-based NPs, as well as exosomes derived from human embryonic stem cells (hESC), human lung cancer (A549) cells, and colorectal cancer (CRC) cells, based solely on their electrokinetic attributes. Comparative analyses involving cross-validation, train-test splits, confusion matrices, and Receiver Operating Characteristic (ROC) curves revealed that classical ML techniques could accurately identify the types of NPs and EVs. Notably, QML demonstrated proficiency in differentiating between various NPs and EVs, including the distinction of EVs in the plasma of CRC patients versus those of healthy individuals. Furthermore, QML's application has been extended to the identification of NPs along with EVs in the plasma of CRC patients and experimental mice, achieving higher prediction performance even with a minimal training dataset, demonstrating that QML based electrokinetic mining could identify NPs or EVs with minimal training data, thereby facilitating novel clinical development in the realm of liquid biopsies. © 2025 The Authors

关键词： Electrokinetic analysis Extracellular vesicle Liquid biopsy Machine learning Nanoparticle Quantum machine learning

来源：评论

学校读者我要写书评

暂无评论

Benchmarking the Immersed Boundary Method for Viscoelastic Flows

arXiv

引用

arXiv 2023年

作者： Gruninger, Cole Barrett, Aaron Fang, Fuhui Forest, M. Gregory Griffith, Boyce E. Department of Mathematics University North Carolina Chapel HillNC United States Department of Mathematics University of Utah Salt Lake CityUT United States Department of Applied Physical Sciences University of North Carolina Chapel HillNC United States Department of Biomedical Engineering University of North Carolina Chapel HillNC United States Carolina Center for Interdisciplinary Applied Mathematics University of North Carolina Chapel HillNC United States Computational Medicine Program University of North Carolina School of Medicine Chapel HillNC United States McAllister Heart Institute University of North Carolina School of Medicine Chapel HillNC United States

We present and analyze a series of benchmark tests regarding the application of the immersed boundary (IB) method to viscoelastic flows through and around non-trivial, stationary geometries. The IB method is widely used for the simulation of biological fluid dynamics and other modeling scenarios where a structure is immersed in a fluid. Although the IB method has been most commonly used to model systems with viscous incompressible fluids, it also can be applied to visoelastic fluids, and has enabled the study of a wide variety of dynamical problems including the settling of vesicles and the swimming of elastic filaments in fluids modeled by the Oldroyd-B constuitive equation. However, to date, relatively little work has explored the accuracy or convergence properties of the numerical scheme. Herein, we present benchmarking results for an IB solver applied to viscoelastic flows in and around non-trivial geometries using the idealized Oldroyd-B and more realistic, polymer-entanglement-based Rolie-Poly constitutive equations. We use two-dimensional numerical test cases along with results from rheology experiments to benchmark the IB method and compare it to more complex finite element and finite volume viscoelastic flow solvers. Additionally, we analyze different choices of regularized delta function and relative Lagrangian grid spacings which allow us to identify and recommend the key choices of these numerical parameters depending on the present flow regime. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Widely Tunable Berry Curvature in the Magnetic Semimetal Cr1+δTe2

引用

Advanced Materials 2023年第12期35卷

作者： Fujisawa, Yuita Pardo-Almanza, Markel Hsu, Chia-Hsiu Mohamed, Atwa Yamagami, Kohei Krishnadas, Anjana Chang, Guoqing Chuang, Feng-Chuan Khoo, Khoong Hong Zang, Jiadong Soumyanarayanan, Anjan Okada, Yoshinori Okinawa904-0495 Japan Department of Physics National Sun Yat-sen University Kaohsiung80424 Taiwan Physics Division National Center for Theoretical Sciences Taipei10617 Taiwan Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University Singapore637371 Singapore Center for Theoretical and Computational Physics National Sun Yat-sen University Kaohsiung80424 Taiwan Institute of High Performance Computing Agency for Science Technology and Research Singapore138632 Singapore Department of Physics and Astronomy University of New Hampshire DurhamNH 03824 United States Materials Science Program University of New Hampshire DurhamNH 03824 United States Department of Physics National University of Singapore Singapore117551 Singapore Institute of Materials Research and Engineering Agency for Science Technology and Research Singapore138634 Singapore

Magnetic semimetals have increasingly emerged as lucrative platforms hosting spin-based topological phenomena in real and momentum spaces. Cr1+δTe2 is a self-intercalated magnetic transition metal dichalcogenide (TMD), which exhibits topological magnetism and tunable electron filling. While recent studies have explored real-space Berry curvature effects, similar considerations of momentum-space Berry curvature are lacking. Here, the electronic structure and transport properties of epitaxial Cr1+δTe2 thin films are systematically investigated over a range of doping, δ (0.33 – 0.71). Spectroscopic experiments reveal the presence of a characteristic semi-metallic band region, which shows a rigid like energy shift with δ. Transport experiments show that the intrinsic component of the anomalous Hall effect (AHE) is sizable and undergoes a sign flip across δ. Finally, density functional theory calculations establish a link between the doping evolution of the band structure and AHE: the AHE sign flip is shown to emerge from the sign change of the Berry curvature, as the semi-metallic band region crosses the Fermi energy. These findings underscore the increasing relevance of momentum-space Berry curvature in magnetic TMDs and provide a unique platform for intertwining topological physics in real and momentum spaces. © 2023 The Authors. Advanced Materials published by Wiley-VCH GmbH.

关键词： Density functional theory

来源：评论

学校读者我要写书评

暂无评论

When data disappear: public health pays as US policy strays

引用

The Lancet Digital Health 2025年 100874页

作者： McAndrew, Thomas Lover, Andrew A Hoyt, Garrik Majumder, Maimuna S Department of Biostatistics and Health Data Science College of Health Lehigh University BethlehemPA United States Department of Biostatistics and Epidemiology School of Public Health and Health Sciences University of Massachusetts Amherst AmherstMA United States Department of Computer Science and Engineering PC Rossin College of Engineering and Applied Sciences Lehigh University BethlehemPA United States Department of Pediatrics Harvard Medical School BostonMA United States Computational Health Informatics Program Boston Children's Hospital BostonMA United States

Presidential actions on Jan 20, 2025, by President Donald Trump, including executive orders, have delayed access to or led to the removal of crucial public health data sources in the USA. The continuous collection and maintenance of health data support public health, safety, and security associated with diseases such as seasonal influenza. To show how public health data surveillance enhances public health practice, we analysed data from seven US Government-maintained sources associated with seasonal influenza. We fit two models that forecast the number of national incident influenza hospitalisations in the USA: (1) a data-rich model incorporating data from all seven Government data sources;and (2) a data-poor model built using a single Government hospitalisation data source, representing the minimal required information to produce a forecast of influenza hospitalisations. The data-rich model generated reliable forecasts useful for public health decision making, whereas the predictions using the data-poor model were highly uncertain, rendering them impractical. Thus, health data can serve as a transparent and standardised foundation to improve domestic and global health. Therefore, a plan should be developed to safeguard public health data as a public good. © 2025 The Author(s)

关键词： Health insurance

来源：评论

学校读者我要写书评

暂无评论

Publisher Correction: Deciphering DNA variant-associated aberrant splicing with the aid of RNA sequencing

引用

Nature genetics 2023年第7期55卷 1251页

作者： Bin Zhang Xin Gao Computer Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia. KAUST Computational Bioscience Research Center King Abdullah University of Science and Technology Thuwal Saudi Arabia. Computer Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia. xin.gao@kaust.edu.sa. KAUST Computational Bioscience Research Center King Abdullah University of Science and Technology Thuwal Saudi Arabia. xin.gao@kaust.edu.sa.

来源：评论

学校读者我要写书评

暂无评论

Syntax-ignorant n-gram embeddings for sentiment analysis of arabic dialects 4

Syntax-ignorant n-gram embeddings for sentiment analysis of ...

引用

4th Arabic Natural Language Processing Workshop, WANLP 2019, held at ACL 2019

作者： Mulki, Hala Haddad, Hatem Gridach, Mourad Babaoǧlu, Ismail Department of Computer Engineering Konya Technical University Turkey Riadi Laboratory National School of Computer Sciences University of Manouba Tunisia Computational Bioscience Program University of Colorado School of Medicine United States ICompass Consulting Tunisia

ISBN: (纸本)9781950737321

Arabic sentiment analysis models have employed compositional embedding features to represent the Arabic dialectal content. These embeddings are usually composed via ordered, syntax-aware composition functions and learned within deep neural frameworks. With the free word order and the varying syntax nature across the different Arabic dialects, a sentiment analysis system developed for one dialect might not be efficient for the others. Here we present syntax-ignorant n-gram embeddings to be used in sentiment analysis of several Arabic dialects. The proposed embeddings were composed and learned using an unordered composition function and a shallow neural model. Five datasets of different dialects were used to evaluate the produced embeddings in the sentiment analysis task. The obtained results revealed that, our syntax-ignorant embeddings could outperform word2vec model and doc2vec both variant models in addition to hand-crafted system baselines, while a competent performance was noticed towards baseline systems that adopted more complicated neural architectures. © ACL *** right reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Theoretical study on adsorption and reaction of polymeric formic acid on the Cu(111) surface

引用

Physical Review Materials 2021年第7期5卷 075801-075801页

作者： Septia Eka Marsha Putra Fahdzi Muttaqien Yuji Hamamoto Kouji Inagaki Akitoshi Shiotari Jun Yoshinobu Yoshitada Morikawa Ikutaro Hamada Department of Precision Engineering Graduate School of Engineering Osaka University 2-1 Yamada-oka Suita Osaka 565-0871 Japan Department of Engineering Physics Institut Teknologi Sumatera Jalan Terusan Ryacudu Way Hui Jati Agung South Lampung 35365 Indonesia Instrumentation and Computational Physics Research Group Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung Jalan Ganesha 10 Bandung West Java 40132 Indonesia Master Program in Computational Science Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung Jalan Ganesha 10 Bandung West Java 40132 Indonesia Elements Strategy Initiative for Catalysts and Batteries (ESICB) Kyoto University Goryo-Ohara Nishikyou-ku Katsura Kyoto 615-8245 Japan Department of Advanced Materials Science The University of Tokyo 5-1-5 Kashiwanoha Kashiwa Chiba 277-8561 Japan The Institute for Solid State Physics The University of Tokyo 5-1-5 Kashiwanoha Kashiwa Chiba 277-8581 Japan Research Center for Precision Engineering Graduate School of Engineering Osaka University 2-1 Yamada-oka Suita Osaka 565-0871 Japan

We investigate the polymeric adsorption of formic acid (HCOOH) on the Cu(111) surface by means of density functional theory. We present structural models for the polymeric form of HCOOH on Cu(111) and characterize their stability, electronic, and vibrational properties. Based on the energetics and dynamics, as well as simulated scanning tunneling microscopy and atomic force microscopy images, we propose that the α polymorph is likely to be formed on the Cu(111) surface and can explain the experimental findings. We also study the initial step of the catalytic dehydrogenation of HCOOH and find that the O-H bond dissociation at the edge of the polymer is facilitated, rather than that forming hydrogen bonding, agreeing well with the experiments.

关键词： Adsorption Chemical bonding Chemical kinetics, dynamics & catalysis Electronic structure Surface & interfacial phenomena Surfaces Density functional theory First-principles calculations

来源：评论

学校读者我要写书评

暂无评论

Microscopic picture of paraelectric perovskites from structural prototypes

引用

Physical Review Research 2022年第1期4卷 L012042-L012042页

作者： Michele Kotiuga Samed Halilov Boris Kozinsky Marco Fornari Nicola Marzari Giovanni Pizzi Theory and Simulation of Materials (THEOS) National Centre for Computational Design and Discovery of Novel Materials (MARVEL) École Polytechnique Fédérale de Lausanne CH-1015 Lausanne Switzerland Designed Material Technologies LLC P.O. Box 14548 Richmond Virginia 23221-9998 USA John A. Paulson School of Engineering and Applied Sciences Harvard University 29 Oxford Street Cambridge Massachusetts 02138 USA Robert Bosch LLC Research and Technology Center Cambridge Massachusetts 02139 USA Department of Physics and Science of Advanced Materials Program Central Michigan University Mt. Pleasant Michigan 48859 USA

We highlight with first-principles molecular dynamics the persistence of intrinsic 〈111〉 Ti off-centerings for BaTiO3 in its cubic paraelectric phase. Intriguingly, these are inconsistent with the Pm3¯m space group often used to atomistically model this phase using density-functional theory or similar methods. Therefore, we deploy a systematic symmetry analysis to construct representative structural models in the form of supercells that satisfy a desired point symmetry but are built from the combination of lower-symmetry primitive cells. We define as structural prototypes the smallest of these that are both energetically and dynamically stable. Remarkably, two 40-atom prototypes can be identified for paraelectric BaTiO3; these are also common to many other ABO3 perovskites. These prototypes can offer structural models of paraelectric phases that can be used for the computational engineering of functional materials. Last, we show that the emergence of B-cation off-centerings and the primitive-cell phonon instabilities is controlled by the equilibrium volume, in turn, dictated by the filler A cation.

关键词： Crystal symmetry Ferroelectricity Structural order parameter Paraelectrics

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：