检索结果-内蒙古大学图书馆

Efficient adaptive exponential time integrators for nonlinear Schrödinger equations with nonlocal potential

Journal of computational mathematics and Data Science 2021年 1卷

作者： Auzinger, Winfried Březinová, Iva Grosz, Alexander Hofstätter, Harald Koch, Othmar Sato, Takeshi Institute of Analysis and Scientific Computing TU Wien Wiedner Hauptstraße 8-10 Wien 1040 Austria Institute of Theoretical Physics TU Wien Wiedner Hauptstraße 8-10 Wien 1040 Austria Institut für Mathematik Universität Wien Oskar-Morgensternplatz 1 Wien 1090 Austria Department of Nuclear Engineering and Management University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-8656 Japan Photon Science Center Graduate School of Engineering The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-8656 Japan Research Institute for Photon Science and Laser Technology The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-0033 Japan Department of Mathematics Technical University of Munich Arcisstraße 21 München D-80333 Germany

The performance of exponential-based numerical integrators for the time propagation of the equations associated with the multiconfiguration time-dependent Hartree–Fock (MCTDHF) method for the approximation of the multi-particle Schrödinger equation in one space dimension is assessed. Among the most popular integrators such as Runge–Kutta methods, time-splitting, exponential integrators and Lawson methods, exponential Lawson multistep methods with one predictor–corrector step provide the best stability and accuracy at the least effort. This assessment is based on the observation that the evaluation of the nonlocal terms associated with the potential is the computationally most demanding part of such a calculation in our setting. In addition, the predictor step provides an estimator for the local time-stepping error, thus allowing for adaptive time-stepping which reflects the smoothness of the solution and enables to reliably control the accuracy of a computation in a robust way, without the need to guess an optimal stepsize a priori. One-dimensional model examples are studied to compare different time integrators and demonstrate the successful application of our adaptive methods. © 2021 The Author(s)

关键词： Adaptive stepsize selection Exponential integrators Lawson methods Local error estimators Multiconfiguration time-dependent Hartree–Fock method Splitting methods

来源：评论

学校读者我要写书评

暂无评论

THU676 Real-time Assessment Of The Beneficial Role Of Computer-Aided Diagnosis In The Diagnosis Of Thyroid Nodules On Ultrasound

引用

Journal of the Endocrine Society 2023年第SUPPLEMENT_1期7卷

作者： Youngsook Kim Sungjae Shin Eunjung Lee Daham Kim Jin Young Kwak Department of Internal Medicine Institute of Endocrine Research Yonsei University College of Medicine Seoul Korea Republic of Department of Internal Medicine National Health Insurance Service Ilsan Hospital Gyeonggi-do Korea Republic of School of Mathematics and Computing (Computational Science and Engineering) Yonsei University Seoul Korea Republic of Department of Radiology Severance Hospital Research Institute of Radiological Science Seoul Korea Republic of

Disclosure: Y. Kim:None.S. Shin:None.E. Lee:None.D. Kim:None.J. Kwak:None.

Disclosure: Y. Kim: None. S. Shin: None. E. Lee: None. D. Kim: None. J. Kwak: None.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lattice studies of Sp(2N) gauge theories using GRID 40

Lattice studies of Sp(2N) gauge theories using GRID

引用

40th International Symposium on Lattice Field Theory, LATTICE 2023

作者： Bennett, Ed Boyle, Peter Del Debbio, Luigi Forzano, Niccolò Hong, Deog Ki Lee, Jong-Wan Lenz, Julian Lin, C.-J. David Lucini, Biagio Lupo, Alessandro Piai, Maurizio Vadacchino, Davide Swansea Academy of Advanced Computing Swansea University Bay Campus Fabian Way Wales SwanseaSA1 8EN United Kingdom School of Physics and Astronomy University of Edinburgh EdinburghEH9 3FD United Kingdom Physics Department Brookhaven National Laboratory UptonNY11973 United States Higgs Centre for Theoretical Physics School of Physics and Astronomy The University of Edinburgh Peter Guthrie Tait Road EdinburghEH9 3FD United Kingdom Department of Physics Faculty of Science and Engineering Swansea University Singleton Park SwanseaSA2 8PP United Kingdom Department of Physics Pusan National University Busan46241 Korea Republic of Institute for Extreme Physics Pusan National University Busan46241 Korea Republic of Daejeon34126 Korea Republic of Institute of Physics National Yang Ming Chiao Tung University 1001 Ta-Hsueh Road Hsinchu30010 Taiwan Centre for High Energy Physics Chung-Yuan Christian University Chung-Li32023 Taiwan Centre for Theoretical and Computational Physics National Yang Ming Chiao Tung University 1001 Ta-Hsueh Road Hsinchu30010 Taiwan Department of Mathematics Faculty of Science and Engineering Swansea University Bay Campus Fabian Way Wales SwanseaSA1 8EN United Kingdom Centre for Mathematical Sciences University of Plymouth PlymouthPL4 8AA United Kingdom

Four-dimensional gauge theories based on symplectic Lie groups provide elegant realisations of the microscopic origin of several new physics models. Numerical studies pursued on the lattice provide quantitative information necessary for phenomenological applications. To this purpose, we implemented Sp(2N) gauge theories using Monte Carlo techniques within Grid, a performant framework designed for the numerical study of quantum field theories on the lattice. We show the first results obtained using this library, focusing on the case-study provided by the Sp(4) theory coupled to Nas = 4 Wilson-Dirac fermions transforming in the 2-index antisymmetric representation. In particular, we discuss preliminary tests of the algorithm and we test some of its main functionalities. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Lattice theory

来源：评论

学校读者我要写书评

暂无评论

Hybrid deep learning and isogeometric analysis for bearing capacity assessment of sand over clay

引用

Journal of Rock Mechanics and Geotechnical engineering 2024年

作者： Toan Nguyen-Minh Tram Bui-Ngoc Jim Shiau Tan Nguyen Trung Nguyen-Thoi Faculty of Civil Engineering Ton Duc Thang University Ho Chi Minh City 700000 Vietnam Laboratory for Computational Mechanics Institute for Computational Science and Artificial Intelligence Van Lang University Ho Chi Minh City 700000 Vietnam Faculty of Mechanical - Electrical and Computer Engineering School of Technology Van Lang University Ho Chi Minh City 700000 Vietnam School of Engineering University of Southern Queensland Toowoomba QLD 4350 Australia Smart Computing in Civil Engineering Research Group Ton Duc Thang University Ho Chi Minh City 700000 Vietnam Laboratory for Applied and Industrial Mathematics Institute for Computational Science and Artificial Intelligence Van Lang University Ho Chi Minh City 700000 Vietnam

In this paper, Isogeometric analysis (IGA) is effectively integrated with machine learning (ML) to investigate the bearing capacity of strip footings in layered soil profiles, with a focus on a sand-over-clay configuration. The study begins with the generation of a comprehensive dataset of 10,000 samples from IGA upper bound (UB) limit analyses, facilitating an in-depth examination of various material and geometric conditions. A hybrid deep neural network, specifically the Whale Optimization Algorithm-Deep Neural Network (WOA-DNN), is then employed to utilize these 10,000 outputs for precise bearing capacity predictions. Notably, the WOA-DNN model outperforms conventional ML techniques, offering a robust and accurate prediction tool. This innovative approach explores a broad range of design parameters, including sand layer depth, load-to-soil unit weight ratio, internal friction angle, cohesion, and footing roughness. A detailed analysis of the dataset reveals the significant influence of these parameters on bearing capacity, providing valuable insights for practical foundation design. This research demonstrates the usefulness of data-driven techniques in optimizing the design of shallow foundations within layered soil profiles, marking a significant stride in geotechnical engineering advancements.

关键词： UB limit analysis Isogeometric analysis (IGA) hybrid deep neural network Whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Verification benchmarks for single-phase flow in three-dimensional fractured porous media

arXiv

引用

arXiv 2020年

作者： Berre, Inga Boon, Wietse M. Flemisch, Bernd Fumagalli, Alessio Gläser, Dennis Keilegavlen, Eirik Scotti, Anna Stefansson, Ivar Tatomir, Alexandru Brenner, Konstantin Burbulla, Samuel Devloo, Philippe Duran, Omar Favino, Marco Hennicker, Julian Lee, I-Hsien Lipnikov, Konstantin Masson, Roland Mosthaf, Klaus Chiara Nestola, Maria Giuseppina Ni, Chuen-Fa Nikitin, Kirill Schädle, Philipp Svyatskiy, Daniil Yanbarisov, Ruslan Zulianp, Patrick Department of Mathematics University of Bergen Allégaten 41 Bergen5007 Norway Department of Mathematics KTH Royal Institute of Technology Lindstedtsvägen 25 Stockholm11428 Sweden Department of Hydromechanics and Modelling of Hydrosystems University of Stuttgart Pfaffenwaldring 61 Stuttgart70569 Germany Laboratory for Modeling and Scientific Computing MOX Politecnico di Milano p.za Leonardo da Vinci 32 Milano20133 Italy Department of Applied Geology Geosciences Center University of Göttingen Goldschmidtstrasse 3 Göttingen37077 Germany Department of Earth Sciences Uppsala University Villavägen 16 UppsalaS-75236 Sweden University of Côte d’Azur CNRS INRIA LJAD Nice France Institute of Applied Analysis and Numerical Simulation University of Stuttgart Pfaffenwaldring 57 Stuttgart70569 Germany FEC Universidade Estadual de Campinas Cidade Universitária R. Josiah Willard Gibbs 85 Campinas-SPCEP 13083-839 Brazil Institute of Earth Sciences University of Lausanne Building Geopolis UNIL-Mouline Lausanne1015 Switzerland Section de Mathématiques Université de Genève 2-4 rue du Lièvre CP 64 Genève1211 Switzerland Graduate Institute of Applied Geology National Central University Taiwan Center for Environmental Studies National Central University Taiwan Los Alamos National Laboratory New Mexico United States Department of Environmental Engineering Technical University of Denmark Bygningstorvet Building 115 Kgs. Lyngby2800 Denmark Numerical Simulation in Science Medicine and Engineering Group Institute of Computational Science Università della Svizzera italiana. Via G. Buffi 13 Lugano Ticino6900 Switzerland Marchuk Institute of Numerical Mathematics of Russian Academy of Sciences Moscow Russia ETH Zürich Geothermal Energy and Geofluids Group Institute of Geophysics Zürich8092 Switzerland

Flow in fractured porous media occurs in the earth’s subsurface, in biological tissues, and in man-made materials. Fractures have a dominating influence on flow processes, and the last decade has seen an extensive development of models and numerical methods that explicitly account for their presence. To support these developments, we present a portfolio of four benchmark cases for single-phase flow in three-dimensional fractured porous media. The cases are specifically designed to test the methods’ capabilities in handling various complexities common to the geometrical structures of fracture networks. Based on an open call for participation, results obtained with 17 numerical methods were collected. This paper presents the underlying mathematical model, an overview of the features of the participating numerical methods, and their performance in solving the benchmark cases. Copyright © 2020, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

DPA-2: a large atomic model as a multi-task learner

arXiv

引用

arXiv 2023年

作者： Zhang, Duo Liu, Xinzijian Zhang, Xiangyu Zhang, Chengqian Cai, Chun Bi, Hangrui Du, Yiming Qin, Xuejian Peng, Anyang Huang, Jiameng Li, Bowen Shan, Yifan Zeng, Jinzhe Zhang, Yuzhi Liu, Siyuan Li, Yifan Chang, Junhan Wang, Xinyan Zhou, Shuo Liu, Jianchuan Luo, Xiaoshan Wang, Zhenyu Jiang, Wanrun Wu, Jing Yang, Yudi Yang, Jiyuan Yang, Manyi Gong, Fu-Qiang Zhang, Linshuang Shi, Mengchao Dai, Fu-Zhi York, Darrin M. Liu, Shi Zhu, Tong Zhong, Zhicheng Lv, Jian Cheng, Jun Jia, Weile Chen, Mohan Ke, Guolin Weinan, E. Zhang, Linfeng Wang, Han AI for Science Institute Beijing100080 China DP Technology Beijing100080 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing100871 China University of Chinese Academy of Sciences Beijing100871 China HEDPS CAPT College of Engineering Peking University Beijing100871 China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo315201 China CAS Key Laboratory of Magnetic Materials and Devices Zhejiang Province Key Laboratory of Magnetic Materials and Application Technology Chinese Academy of Sciences Ningbo315201 China School of Electronics Engineering and Computer Science Peking University Beijing100871 China Shanghai Engineering Research Center of Molecular Therapeutics & New Drug Development School of Chemistry and Molecular Engineering East China Normal University Shanghai200062 China Laboratory for Biomolecular Simulation Research Institute for Quantitative Biomedicine Department of Chemistry and Chemical Biology Rutgers University PiscatawayNJ08854 United States Department of Chemistry Princeton University PrincetonNJ08540 United States College of Chemistry and Molecular Engineering Peking University Beijing100871 China Yuanpei College Peking University Beijing100871 China School of Electrical Engineering and Electronic Information Xihua University Chengdu610039 China State Key Laboratory of Superhard Materials College of Physics Jilin University Changchun130012 China Key Laboratory of Material Simulation Methods & Software of Ministry of Education College of Physics Jilin University Changchun130012 China International Center of Future Science Jilin University Changchun130012 China Key Laboratory for Quantum Materials of Zhejiang Province Department of Physics School of Science Westlake University Zhejiang Hangzhou310030 China Atomistic Simulations Italia

The rapid advancements in artificial intelligence (AI) are catalyzing transformative changes in atomic modeling, simulation, and design. AI-driven potential energy models have demonstrated the capability to conduct large-scale, long-duration simulations with the accuracy of ab initio electronic structure methods. However, the model generation process remains a bottleneck for large-scale applications. We propose a shift towards a model-centric ecosystem, wherein a large atomic model (LAM), pre-trained across multiple disciplines, can be efficiently fine-tuned and distilled for various downstream tasks, thereby establishing a new framework for molecular modeling. In this study, we introduce the DPA-2 architecture as a prototype for LAMs. Pre-trained on a diverse array of chemical and materials systems using a multi-task approach, DPA-2 demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning methodologies. Our approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research. Copyright © 2023, The Authors. All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing quantum control by bootstrapping a quantum processor of 12 qubits

arXiv

引用

arXiv 2017年

作者： Lu, Dawei Li, Keren Li, Jun Katiyar, Hemant Park, Annie Jihyun Feng, Guanru Xin, Tao Li, Hang Long, Guilu Brodutch, Aharon Baugh, Jonathan Zeng, Bei Laflamme, Raymond Department of Physics Southern University of Science and Technology Shenzhen518055 China Institute for Quantum Computing Department of Physics and Astronomy University of Waterloo WaterlooONN2L 3G1 Canada State Key Laboratory of Low-Dimensional Quantum Physics Department of Physics Tsinghua University Beijing100084 China Beijing Computational Science Research Center Beijing100193 China Max-Planck-Institutfür Quantenoptik GarchingD-85748 Germany Center for Quantum Information and Quantum Control Department of Physics Department of Electrical and Computer Engineering University of Toronto TorontoONM5S 3H6 Canada Department of Mathematics and Statistics University of Guelph GuelphONN1G 2W1 Canada Perimeter Institute for Theoretical Physics Waterloo ONN2L 2Y5 Canada

Accurate and efficient control of quantum systems is one of the central challenges for quantum information processing. Current state-of-the-art experiments rarely go beyond 10 qubits and in most cases demonstrate only limited control. Here we demonstrate control of a 12-qubit system, and show that the system can be employed as a quantum processor to optimize its own control sequence by using measurement-based feedback control (MQFC). The final product is a control sequence for a complex 12-qubit task: preparation of a 12-coherent state. The control sequence is about 10% more accurate than the one generated by the standard (classical) technique, showing that MQFC can correct for unknown imperfections. Apart from demonstrating a high level of control over a relatively large system, our results show that even at the 12-qubit level, a quantum processor can be a useful lab instrument. As an extension of our work, we propose a method for combining the MQFC technique with a twirling protocol, to optimize the control sequence that produces a desired Clifford gate. Copyright © 2017, The Authors. All rights reserved.

关键词： Quantum optics

来源：评论

学校读者我要写书评

暂无评论

Black hole spectroscopy for precessing binary black hole coalescences

arXiv

引用

arXiv 2023年

作者： Zhu, Hengrui Siegel, Harrison Mitman, Keefe Isi, Maximiliano Farr, Will M. Boyle, Michael Deppe, Nils Kidder, Lawrence E. Ma, Sizheng Moxon, Jordan Nelli, Kyle C. Pfeiffer, Harald P. Scheel, Mark A. Teukolsky, Saul A. Throwe, William Varma, Vijay Vu, Nils L. Department of Physics Princeton University Jadwin Hall Washington Road NJ08544 United States Princeton Gravity Initiative Princeton University PrincetonNJ08544 United States Department of Physics Columbia University 704 Pupin Hall 538 West 120th Street New YorkNY10027 United States Center for Computational Astrophysics Flatiron Institute New YorkNY10010 United States Walter Burke Institute for Theoretical Physics California Institute of Technology PasadenaCA91125 United States Department of Physics and Astronomy Stony Brook University Stony BrookNY11794 United States Cornell Center for Astrophysics and Planetary Science Cornell University IthacaNY14853 United States Department of Physics Cornell University IthacaNY14853 United States Perimeter Institute for Theoretical Physics 31 Caroline Streeth North WaterlooONNSL 2Y5 Canada Am Mühlenberg 1 PotsdamD-14476 Germany Department of Mathematics Center for Scientific Computing and Data Science Research University of Massachusetts DartmouthMA02747 United States

The spectroscopic study of black hole quasinormal modes in gravitational-wave ringdown observations is hindered by our ignorance of which modes should dominate astrophysical signals for different binary configurations, limiting tests of general relativity and astrophysics. In this work, we present a description of the quasinormal modes that are excited in the ringdowns of comparable mass, quasi-circular precessing binary black hole coalescences—a key region of parameter space that has yet to be fully explored within the framework of black hole spectroscopy. We suggest that the remnant perturbation for precessing and non-precessing systems is approximately the same up to a rotation, which implies that the relative amplitudes of the quasinormal modes in both systems are also related by a rotation. We present evidence for this by analyzing an extensive catalog of numerical relativity simulations. Additional structure in the amplitudes is connected to the system’s kick velocity and other asymmetries in the orbital dynamics. We find that the ringdowns of precessing systems need not be dominated by the (, m) = (2, ±2) quasinormal modes, and that instead the (2, ±1) or (2, 0) quasinormal modes can dominate. Our results are consistent with a ringdown analysis of the LIGO-Virgo gravitational wave signal GW190521, and may also help in understanding phenomenological inspiral-merger-ringdown waveform model systematics. © 2023, CC BY.

关键词： Relativity

来源：评论

学校读者我要写书评

暂无评论

Perspectives on adaptive dynamical systems

arXiv

引用

arXiv 2023年

作者： Sawicki, Jakub Berner, Rico Loos, Sarah A.M. Anvari, Mehrnaz Bader, Rolf Barfuss, Wolfram Botta, Nicola Brede, Nuria Franović, Igor Gauthier, Daniel J. Goldt, Sebastian Hajizadeh, Aida Hövel, Philipp Karin, Omer Lorenz-Spreen, Philipp Miehl, Christoph Mölter, Jan Olmi, Simona Schöll, Eckehard Seif, Alireza Tass, Peter A. Volpe, Giovanni Yanchuk, Serhiy Kurths, Jürgen Potsdam Institute for Climate Impact Research Telegrafenberg Potsdam14473 Germany Fachhochschule Nordwestschweiz FHNW Leonhardsstrasse 6 Basel4009 Switzerland Department of Physics Humboldt-Universität zu Berlin Newtonstraße 15 Berlin12489 Germany DAMTP University of Cambridge Wilberforce Road CambridgeCB3 0WA United Kingdom Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven Sankt-Augustin53757 Germany Institute of Systematic Musicology University of Hamburg Germany Transdisciplinary Research Area: Sustainable Futures University of Bonn Bonn53113 Germany University of Bonn Bonn53113 Germany Department of Computer Science and Engineering Chalmers University of Technology Göteborg412 96 Sweden Department of Computer Science University of Potsdam An der Bahn 2 Potsdam14476 Germany Scientific Computing Laboratory Center for the Study of Complex Systems Institute of Physics Belgrade University of Belgrade Pregrevica 118 Belgrade11080 Serbia The Ohio State University Department of Physics and Electrical and Computer Engineering 191 West Woodruff Ave ColumbusOH43210 United States ResCon Technologies LLC 1275 Kinnear Rd. Suite 239 ColumbusOH43212 United States Trieste Italy Research Group Comparative Neuroscience Leibniz Institute for Neurobiology Magdeburg Germany Theoretical Physics Saarland University Saarbrücken66123 Germany Center for Biophysics Saarland University Saarbrücken66123 Germany Department of Mathematics Imperial College London United Kingdom Center for Adaptive Rationality Max Planck Institute for Human Development Lentzeallee 94 Berlin14195 Germany Max Planck Institute for Brain Research Max-von-Laue-Straße 4 Frankfurt am Main60438 Germany Technical University of Munich School of Life Sciences Alte Akademie 8 Freising85354 Germany Department of Mathematics School of Computation Information and Technology Technical University of Munich Boltzmannstraße 3 Garching bei München8574

Adaptivity is a dynamical feature that is omnipresent in nature, socio-economics, and technology. For example, adaptive couplings appear in various real-world systems like the power grid, social, and neural networks, and they form the backbone of closed-loop control strategies and machine learning algorithms. In this article, we provide an interdisciplinary perspective on adaptive systems. We reflect on the notion and terminology of adaptivity in different disciplines and discuss which role adaptivity plays for various fields. We highlight common open challenges, and give perspectives on future research directions, looking to inspire interdisciplinary approaches. Copyright © 2023, The Authors. All rights reserved.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Position: Bayesian deep learning is needed in the age of large-scale AI 24

Position: Bayesian deep learning is needed in the age of lar...

引用

Proceedings of the 41st International Conference on Machine Learning

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

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.

关键词：

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：