检索结果-内蒙古大学图书馆

iGEM: a model system for team science and innovation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Santolini, Marc Blondel, Leo Palmer, Megan J. Ward, Robert N. Jeyaram, Rathin Brink, Kathryn R. Krishna, Abhijeet Barabási, Albert-László Université Paris Cité Inserm System Engineering and Evolution Dynamics ParisF-75004 France Learning Planet Institute ParisF-75004 France Network Science Institute Department of Physics Northeastern University BostonMA02115 United States Department of Bioengineering Stanford University StanfordCA United States Center for International Security and Cooperation Stanford University StanfordCA United States School of Public Policy Georgia Institute of Technology AtlantaGA United States Channing Division of Network Medicine Department of Medicine Brigham and Women’s Hospital Harvard Medical School BostonMA United States Department of Network and Data Science Central European University Budapest Hungary

Teams are a primary source of innovation in science and technology. Rather than examining the lone genius, scholarly and policy attention has shifted to understanding how team interactions produce new and useful ideas. Yet the organizational roots of innovation remain unclear, in part because of the limitations of current data. This paper introduces the international Genetically Engineered Machine (iGEM) competition, a model system for studying team science and innovation. By combining digital laboratory notebooks with performance data from 2,406 teams over multiple years of participation, we reveal shared dynamical and organizational patterns across teams and identify features associated with team performance and success. This dataset makes visible organizational behavior that is typically hidden, and thus understudied, creating new opportunities for the science of science and innovation. © 2023, CC BY.

关键词：

On ADMM in deep learning: convergence and saturation-avoidance

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine learning Research 2021年第1期22卷 9024-9090页

作者： Jinshan Zeng Shao-Bo Lin Yuan Yao Ding-Xuan Zhou School of Computer and Information Engineering Jiangxi Normal University Nanchang China and Liu Bie Ju Centre for Mathematical Sciences City University of Hong Kong Hong Kong and Department of Mathematics Hong Kong University of Science and Technology Hong Kong Center of Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University Xi'an China Department of Mathematics Hong Kong University of Science and Technology Hong Kong School of Data Science and Department of Mathematics City University of Hong Kong Hong Kong

In this paper, we develop an alternating direction method of multipliers (ADMM) for deep neural networks training with sigmoid-type activation functions (called sigmoid-ADMM pair), mainly motivated by the gradient-free nature of ADMM in avoiding the saturation of sigmoid-type activations and the advantages of deep neural networks with sigmoid-type activations (called deep sigmoid nets) over their rectified linear unit (ReLU) counterparts (called deep ReLU nets) in terms of approximation. In particular, we prove that the approximation capability of deep sigmoid nets is not worse than that of deep ReLU nets by showing that ReLU activation function can be well approximated by deep sigmoid nets with two hidden layers and finitely many free parameters but not vice-verse. We also establish the global convergence of the proposed ADMM for the nonlinearly constrained formulation of the deep sigmoid nets training from arbitrary initial points to a Karush-Kuhn-Tucker (KKT) point at a rate of order O(1/k). Besides sigmoid activation, such a convergence theorem holds for a general class of smooth activations. Compared with the widely used stochastic gradient descent (SGD) algorithm for the deep ReLU nets training (called ReLU-SGD pair), the proposed sigmoid-ADMM pair is practically stable with respect to the algorithmic hyperparameters including the learning rate, initial schemes and the pro-processing of the input data. Moreover, we find that to approximate and learn simple but important functions the proposed sigmoid-ADMM pair numerically outperforms the ReLU-SGD pair.

关键词： deep learning ADMM sigmoid global convergence saturation avoidance

Consensus-Based Optimization Methods Converge Globally

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fornasier, Massimo Klock, Timo Riedl, Konstantin Technical University of Munich School of Computation Information and Technology Department of Mathematics Munich Germany Munich Center for Machine Learning Munich Germany Munich Data Science Institute Munich Germany Simula Research Laboratory Department of Numerical Analysis and Scientific Computing Oslo Norway University of San Diego Department of Mathematics San DiegoCA United States

In this paper, we study consensus-based optimization (CBO), which is a multi-agent metaheuristic derivative-free optimization method that can globally minimize nonconvex nonsmooth functions and is amenable to theoretical analysis. Based on an experimentally supported intuition that, on average, CBO performs a gradient descent of the squared Euclidean distance to the global minimizer, we devise a novel technique for proving the convergence to the global minimizer in mean-field law for a rich class of objective functions. The result unveils internal mechanisms of CBO that are responsible for the success of the method. In particular, we prove that CBO performs a convexification of a large class of optimization problems as the number of optimizing agents goes to infinity. Furthermore, we improve prior analyses by requiring mild assumptions about the initialization of the method and by covering objectives that are merely locally Lipschitz continuous. As a core component of this analysis, we establish a quantitative nonasymptotic Laplace principle, which may be of independent interest. From the result of CBO convergence in mean-field law, it becomes apparent that the hardness of any global optimization problem is necessarily encoded in the rate of the mean-field approximation, for which we provide a novel probabilistic quantitative estimate. The combination of these results allows to obtain probabilistic global convergence guarantees of the numerical CBO *** Codes 65K10, 90C26, 90C56, 35Q90, 35Q84 Copyright © 2021, The Authors. All rights reserved.

关键词： Fokker Planck equation

Correction: Multivariate clustering for maximizing the small cell users’ performance based on the dynamic interference alignment

学校读者我要写书评

暂无评论

Wireless Networks 2023年第1期30卷 593-593页

作者： Dakshinamoorthy, Prabakar Vaitilingam, Saminadan Sundar, Ramesh Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur India Department of Electronics and Communication Engineering Puducherry Technological University Puducherry India Department of Artificial Intelligence and Machine Learning Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

On the Utility Function of Experiments in Fundamental Science

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Dorigo, Tommaso Doro, Michele Aehle, Max Gauger, Nicolas R. Awais, Muhammad Izbicki, Rafael Kieseler, Jan Masserano, Luca Nardi, Federico Vergara, Luis Recabarren Luleå University of Technology Laboratorievägen 14 Luleå97187 Sweden INFN - Sezione di Padova via F. Marzolo 8 Padova35131 Italy Universal Scientific Education and Research Network Italy Università di Padova Dipartimento di Fisica e Astronomia "G.Galilei" via F. Marzolo 8 Padova35131 Italy Gottlieb-Daimler-Strase Kaiserslautern67663 Germany Karlsruhe Institute for Technology Kaiserstrase 12 Karlsruhe76131 Germany Laboratoire de Physique de Clermont Auvergne 4 Avenue Blaise Pascal Aubière63170 France Centro di Ateneo di Studi e Attività Spaziali "Giuseppe Colombo" Via Venezia 15 PadovaI-35131 Italy Department of Statistics & Data Science Department of Machine Learning Carnegie Mellon University Pittsburgh United States Department of Statistics Federal University of São Carlos São Carlos Brazil

The majority of experiments in fundamental science today are designed to be multi-purpose: their aim is not simply to measure a single physical quantity or process, but rather to enable increased precision in the measurement of a number of different observable quantities of a natural system, to extend the search for new phenomena, or to exclude a larger phase space of candidate theories. Most of the time, a combination of the above goals is pursued;this breadth of scope adds a layer of complexity to the already demanding task of designing the measurement apparatus in an optimal way, by defining suitable geometries and choosing the most advantageous materials and appropriate detection technologies. The precise definition of a global optimality criterion may then require experimentalists to find a consensus on the relative scientific worth of those goals. In this work, we discuss the problem of formulating a utility function for multipurpose experiments, as an enabling step to employ artificial intelligence tools to explore the design space and assist humans in finding solutions at the Pareto front. Copyright © 2025, The Authors. All rights reserved.

关键词： Phase space methods

Traffic4cast at NeurIPS 2021 – Temporal and Spatial Few-Shot Transfer learning in Gridded Geo-Spatial Processes

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Eichenberger, Christian Neun, Moritz Martin, Henry Herruzo, Pedro Spanring, Markus Lu, Yichao Choi, Sungbin Konyakhin, Vsevolod Lukashina, Nina Shpilman, Aleksei Wiedemann, Nina Raubal, Martin Wang, Bo Vu, Hai L. Mohajerpoor, Reza Cai, Chen Kim, Inhi Hermes, Luca Melnik, Andrew Velioglu, Riza Vieth, Markus Schilling, Malte Bojesomo, Alabi Al Marzouqi, Hasan Liatsis, Panos Santokhi, Jay Hillier, Dylan Yang, Yiming Sarwar, Joned Jordan, Anna Hewage, Emil Jonietz, David Tang, Fei Gruca, Aleksandra Kopp, Michael Kreil, David Hochreiter, Sepp Vienna Austria Institute of Cartography and Geoinformation ETH Zurich Switzerland Layer 6 AI Toronto Canada ITMO University Saint Petersburg Russia JetBrains Research Saint Petersburg Russia HSE University Saint Petersburg Russia Institute of Transport Studies Monash University ClaytonVIC Australia CSIRO’s Data61 Eveleigh Australia Institute Civil and Environmental Engineering Department Kongju National University Korea Republic of Machine Learning & Neuroinformatics Group Bielefeld University Germany Electrical Engineering and Computer Science Department Khalifa University Abu Dhabi United Arab Emirates Alchera Data Technologies Ltd Cambridge United Kingdom HERE Technologies Zurich Switzerland Silesian University of Technology Gliwice Poland Machine Learning Institute Johannes Kepler University Linz Austria

The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that neural networks can successfully predict future traffic conditions 1 hour into the future on simply aggregated GPS probe data in time and space bins. We thus reinterpreted the challenge of forecasting traffic conditions as a movie completion task. U-Nets proved to be the winning architecture, demonstrating an ability to extract relevant features in this complex real-world geo-spatial process. Building on the previous competitions, Traffic4cast 2021 now focuses on the question of model robustness and generalizability across time and space. Moving from one city to an entirely different city, or moving from pre-COVID times to times after COVID hit the world thus introduces a clear domain shift. We thus, for the first time, release data featuring such domain shifts. The competition now covers ten cities over 2 years, providing data compiled from over 1012 GPS probe data. Winning solutions captured traffic dynamics sufficiently well to even cope with these complex domain shifts. Surprisingly, this seemed to require only the previous 1h traffic dynamic history and static road graph as input. © 2022, CC BY-NC-SA.

关键词： Probes

Traffic4cast at NeurIPS 2022 – Predict Dynamics along Graph Edges from Sparse Node data: Whole City Traffic and ETA from Stationary Vehicle Detectors

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Neun, Moritz Eichenberger, Christian Martin, Henry Spanring, Markus Siripurapu, Rahul Springer, Daniel Deng, Leyan Wu, Chenwang Lian, Defu Zhou, Min Lumiste, Martin Ilie, Andrei Wu, Xinhua Lyu, Cheng Lu, Qing-Long Mahajan, Vishal Lu, Yichao Li, Jiezhang Li, Junjun Gong, Yue-Jiao Grötschla, Florian Mathys, Joël Wei, Ye Haitao, He Fang, Hui Malm, Kevin Tang, Fei Kopp, Michael Kreil, David Hochreiter, Sepp Vienna Austria Institute of Cartography and Geoinformation ETH Zurich Switzerland School of Data Science University of Science and Technology of China China Huawei Noah’s Ark Lab Bolt Technology Tallinn Estonia University of Bucharest Bucharest Romania Department of Civil and Environmental Engineering Northeastern University BostonMA United States Transportation Systems Engineering Technical University of Munich Germany Layer 6 AI Toronto Canada School of Coumpute Science and Engineering South China University of Technology Guangzhou China ETH Zurich Switzerland Department of Computer Science Loughborough University Loughborough United Kingdom School of Architecture Building and Civil Engineering Loughborough University Loughborough United Kingdom HERE Technologies ChicagoIL United States Kaiko Zurich Switzerland Machine Learning Institute Johannes Kepler University Linz Austria

The global trends of urbanization and increased personal mobility force us to rethink the way we live and use urban space. The Traffic4cast competition series tackles this problem in a data-driven way, advancing the latest methods in machine learning for modeling complex spatial systems over time. In this edition, our dynamic road graph data combine information from road maps, 1012 probe data points, and stationary vehicle detectors in three cities over the span of two years. While stationary vehicle detectors are the most accurate way to capture traffic volume, they are only available in few locations. Traffic4cast 2022 explores models that have the ability to generalize loosely related temporal vertex data on just a few nodes to predict dynamic future traffic states on the edges of the entire road graph. In the core challenge, participants are invited to predict the likelihoods of three congestion classes derived from the speed levels in the GPS data for the entire road graph in three cities 15 min into the future. We only provide vehicle count data from spatially sparse stationary vehicle detectors in these three cities as model input for this task. The data are aggregated in 15 min time bins for one hour prior to the prediction time. For the extended challenge, participants are tasked to predict the average travel times on super-segments 15 min into the future – super-segments are longer sequences of road segments in the graph. The competition results provide an important advance in the prediction of complex city-wide traffic states just from publicly available sparse vehicle data and without the need for large amounts of real-time floating vehicle data. © 2023, CC BY-NC-SA.

关键词： Travel time

data sharing in learning analytics: how context and group discussion influence the individual willingness to share

学校读者我要写书评

暂无评论

Humanities and Social Sciences Communications

Humanities and Social Sciences Communications 2025年第1期12卷 1-13页

作者： Louis Longin Deisy Briceno Oleksandra Poquet Faculty of Philosophy Philosophy of Science and the Study of Religion Ludwig-Maximilians-Universität München Munich Germany LEAPS Lab—LEarning Analytics and Practices in Systems Department of Educational Sciences School of Social Sciences and Technology Technical University of Munich Munich Germany Munich Data Science Institute Technical University of Munich Munich Germany Centre for Change and Complexity in Learning University of South Australia Adelaide Australia

The ethical integration of the data generated by learners into educational practices is of great importance now that data-rich technologies are prevalent in education. Despite the common agreement that learners should have agency in deciding what to do with their data, existing ethical discussions focus on policies or algorithms, with limited attention to participatory learner practices. Participatory practices, particularly around informed consent, can support ethical and meaningful engagement with data sharing decisions. Using a novel experimental methodology, we explored how the decision context influences the perceived acceptability for sharing learning data. We found that participants became more cautious in sharing their data in and after a group discussion. The willingness to share was the lowest when these data were submitted to a government entity and for a collective benefit. Further network analysis of group discussions confirmed the observed attitude shifts: participants consistently discussed different aspects of sharing learning data based on the context such as sharing process vs outcome-related learning data. The results suggest that educational data consent is contextual and that perceptions of privacy in educational technology may differ from those in health contexts. The proposed method of interactive consent, therefore, not only contributes to theories explaining privacy and effective data collection but also represents a new way of conceptualising and realising participatory informed consent.

关键词：

Goodness-of-fit tests for Laplace, Gaussian and exponential power distributions based onλ-th power skewness and kurtosis

学校读者我要写书评

暂无评论

Series Statistics 2023年第1期57卷 94-122页

作者： Alain Desgagné Pierre Lafaye de Micheaux Frédéric Ouimet a Département de Mathématiques Université du Québec à Montréal Montréal Canada b AMIS Université Paul-Valéry Montpellier 3 Montpellier Francec PreMeDICaL - Precision Medicine by Data Integration and Causal Learning Inria Sophia Antipolis Franced Desbrest Institute of Epidemiology and Public Health Université de Montpellier Montpellier Francee School of Mathematics and Statistics UNSW Sydney NSW Australia f Division of Physics Mathematics and Astronomy California Institute of Technology Pasadena CA USAg Department of Mathematics and Statistics McGill University Montreal Canadah Centre de recherches Mathématiques Université de Montréal Montréal Canada

Temperature data, like many other measurements in quantitative fields, are usually modelled using a normal distribution. However, some distributions can offer a better fit while avoiding underestimation of tail event probabilities. To this point, we extend Pearson's notions of skewness and kurtosis to build a powerful family of goodness-of-fit tests based on Rao's score for the exponential power distributionEPDλ(μ,σ), including tests for normality and Laplacity whenλis set to 1 or 2. We find the asymptotic distribution of our test statistic, which is the sum of the squares of twoZ-scores, under the null and under local alternatives. We also develop an innovative regression strategy to obtainZ-scores that are nearly independent and distributed as standard Gaussians, resulting in aχ22distribution valid for any sample size (up to very high precision forn≥20). The caseλ=1leads to a powerful test of fit for the Laplace(μ,σ) distribution, whose empirical power is superior to all 39 competitors in the literature, over a wide range of 400 alternatives. Theoretical proofs in this case are particularly challenging and substantial. We applied our tests to three temperature datasets. The new tests are implemented in theRpackagePoweR.

关键词： asymmetric power distribution Lagrange multiplier test local alternatives power analysis Rao's score test temperature data Primary: 62F03 Secondary: 62E20 62F12 60F05