检索结果-内蒙古大学图书馆

Conditional molecular design with deep generative models

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Kang, Seokho Cho, Kyunghyun Department of Systems Management Engineering Sungkyunkwan University 2066 Seobu-ro Jangan-gu Suwon16419 Korea Republic of Department of Computer Science Center for Data Science New York University 60 5th Avenue New YorkNY10011 United States Facebook AI Research 770 Broadway New YorkNY10003 United States CIFAR Azrieli Global Scholar Canadian Institute for Advanced Research 661 University Avenue TorontoONM5G 1M1 Canada

Although machine learning has been successfully used to propose novel molecules that satisfy desired properties, it is still challenging to explore a large chemical space efficiently. In this paper, we present a conditional molecular design method that facilitates generating new molecules with desired properties. The proposed model, which simultaneously performs both property prediction and molecule generation, is built as a semi-supervised variational autoencoder trained on a set of existing molecules with only a partial annotation. We generate new molecules with desired properties by sampling from the generative distribution estimated by the model. We demonstrate the effectiveness of the proposed model by evaluating it on drug-like molecules. The model improves the performance of property prediction by exploiting unlabeled molecules, and efficiently generates novel molecules fulfilling various target conditions. Copyright © 2018, The Authors. All rights reserved.

关键词： Molecules

A Practically Competitive and Provably Consistent Algorithm for Uplift Modeling

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Zhao, Yan Fang, Xiao Simchi-Levi, David Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States Institute for Data Systems and Society Department of Civil and Environmental Engineering Operations Research Center Massachusetts Institute of Technology CambridgeMA02139 United States

Randomized experiments have been critical tools of decision making for decades. However, subjects can show significant heterogeneity in response to treatments in many important applications. Therefore it is not enough to simply know which treatment is optimal for the entire population. What we need is a model that correctly customize treatment assignment base on subject characteristics. The problem of constructing such models from randomized experiments data is known as Uplift Modeling in the literature. Many algorithms have been proposed for uplift modeling and some have generated promising results on various data sets. Yet little is known about the theoretical properties of these algorithms. In this paper, we propose a new tree-based ensemble algorithm for uplift modeling. Experiments show that our algorithm can achieve competitive results on both synthetic and industry-provided data. In addition, by properly tuning the"node size" parameter, our algorithm is proved to be consistent under mild regularity conditions. This is the first consistent algorithm for uplift modeling that we are aware of. Copyright © 2017, The Authors. All rights reserved.

关键词： Decision making

Ten simple rules for reproducible research in jupyter notebooks

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Rule, Adam Birmingham, Amanda Zuniga, Cristal Altintas, Ilkay Huang, Shih-Cheng Knight, Rob Moshiri, Niema Nguyen, Mai H. Rosenthal, Sara Brin Pérez, Fernando Rose, Peter W. Design Lab UC San Diego San DiegoCA United States Center for Computational Biology and Bioinformatics UC San Diego San DiegoCA United States Department of Pediatrics UC San Diego San DiegoCA United States Data Science Hub San Diego Supercomputer Center UC San Diego San DiegoCA United States Departments of Bioengineering and Computer Science and Engineering Center for Microbiome Innovation UC San Diego San DiegoCA United States Bioinformatics and Systems Biology Graduate Program UC San Diego San DiegoCA United States Department of Statistics Berkeley Institute for Data Science UC Berkeley Lawrence Berkeley National Laboratory BerkeleyCA United States Biomedical Informatics Graduate Program Stanford University StanfordCA United States

Reproducibility of computational studies is a hallmark of scientific methodology. It enables researchers to build with confidence on the methods and findings of others, reuse and extend computational pipelines, and thereby drive scientific progress. Since many experimental studies rely on computational analyses, biologists need guidance on how to set up and document reproducible data analyses or simulations. In this paper, we address several questions about reproducibility. For example, what are the technical and non-technical barriers to reproducible computational studies? What opportunities and challenges do computational notebooks offer to overcome some of these barriers? What tools are available and how can they be used effectively? We have developed a set of rules to serve as a guide to scientists with a specific focus on computational notebook systems, such as Jupyter Notebooks, which have become a tool of choice for many applications. Notebooks combine detailed workflows with narrative text and visualization of results. Combined with software repositories and open source licensing, notebooks are powerful tools for transparent, collaborative, reproducible, and reusable data analyses. Copyright © 2018, The Authors. All rights reserved.

关键词： Digital storage

Generalized Fréchet bounds for cell entries in multidimensional contingency tables

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Uhler, Caroline Richards, Donald Laboratory for Information and Decision Systems Department of Electrical Engineering and Computer Science Institute for Data Systems and Society Massachusetts Institute of Technology CambridgeMA02139 United States Department of Statistics Pennsylvania State University University ParkPA16802 United States

We consider the lattice, L, of all subsets of a multidimensional contingency table and establish the properties of monotonicity and supermodularity for the marginalization function, n(·), on L. We derive from the supermodularity of n(·) some generalized Fréchet inequalities complementing and extending inequalities of Dobra and Fienberg. Further, we construct new monotonic and supermodular functions from n(·), and we remark on the connection between supermodularity and some correlation inequalities for probability distributions on lattices. We also apply an inequality of Ky Fan to derive a new approach to Fréchet inequalities for multidimensional contingency *** 2010 subject classifications: Primary 06D05, 62H17;Secondary 05A20, *** Codes 06D05, 62H17 (Primary), 05A20, 62J12 (Secondary) Copyright © 2017, The Authors. All rights reserved.

关键词： Probability distributions

Analysis on Representative Papers of Applicant for National Natural science Fund for Distinguished Young Scholars in Automation Discipline

学校读者我要写书评

暂无评论

Zidonghua Xuebao/Acta Automatica Sinica 2017年第9期43卷 1673-1676页

作者： Wang, Chen Mao, Rui Wang, Cheng-Hong Chen, Yan College of Engineering Peking University Beijing100871 China 93460 Troop of the PLA Beijing101407 China Department of Information Sciences National Natural Science Foundation of China Beijing100085 China Institute of Big Data and Internet Innovation Hunan university of Commerce Changsha410205 China

We investigates the distribution of the representative papers of the applicant for National Natural science Fund for Distinguished Young Scholars in automation domain from 2013 to 2015. Our result shows that applicants' choices of flve representative papers are not obviously related to the Journal Impact Factor from journal citation report (JCR) or JCR Journal Partition data Platform of the Chinese Academy of sciences. This implies that the academic appraisal systems based on these two commonly used indexes have limitations. We believe it is possible to build a novel index system for journal evaluation and an academic appraisal system, which can fit the intrinsic characteristics of each research domain. Copyright © 2017 Acta Automatica Sinica. All rights reserved.

关键词： Automation

A common trajectory recapitulated by urban economies

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Hong, Inho Frank, Morgan R. Rahwan, Iyad Jung, Woo-Sung Youn, Hyejin Department of Physics Pohang University of Science and Technology Pohang37673 Korea Republic of Media Laboratory Massachusetts Institute of Technology CambridgeMA02139 United States Institute for Data Systems and Society Massachusetts Institute of Technology CambridgeMA02139 United States Department of Industrial and Management Engineering Pohang University of Science and Technology Pohang37673 Korea Republic of Asia Pacific Center for Theoretical Physics Pohang37673 Korea Republic of Kellogg School of Management Northwestern University EvanstonIL60208 United States Northwestern Institute on Complex Systems EvanstonIL60208 United States London Mathematical Lab LondonWC2N 6DF United Kingdom Santa Fe Institute 1399 Hyde Park Road Santa FeNM87501 United States

Is there a general economic pathway recapitulated by individual cities over and over? Identifying such evolution structure, if any, would inform models for the assessment, maintenance, and forecasting of urban sustainability and economic success as a quantitative baseline. This premise seems to contradict the existing body of empirical evidences for path-dependent growth shaping the unique history of individual cities. And yet, recent empirical evidences and theoretical models have amounted to the universal patterns, mostly size-dependent, thereby expressing many of urban quantities as a set of simple scaling laws. Here, we provide a mathematical framework to integrate repeated cross-sectional data, each of which freezes in time dimension, into a frame of reference for longitudinal evolution of individual cities in time. Using data of over 100 millions employment in thousand business categories between 1998 and 2013, we decompose each city’s evolution into a pre-factor and relative changes to eliminate national and global effects. In this way, we show the longitudinal dynamics of individual cities recapitulate the observed cross-sectional regularity. Larger cities are not only scaled-up versions of their smaller peers but also of their past. In addition, our model shows that both specialization and diversification are attributed to the distribution of industry’s scaling exponents, resulting a critical population of 1.2 million at which a city makes an industrial transition into innovative economies. Copyright © 2018, The Authors. All rights reserved.

关键词：

Equivalency of the diagnostic accuracy of the PHQ-8 and PHQ-9: a systematic review and individual participant data meta-analysis (vol 50, pg 1368, 2020)

学校读者我要写书评

暂无评论

PSYCHOLOGICAL MEDICINE 2020年第16期50卷 2816-2816页

作者： Wu, Yin Levis, Brooke Riehm, Kira E. Saadat, Nazanin Levis, Alexander W. Azar, Marleine Rice, Danielle B. Boruff, Jill Cuijpers, Pim Gilbody, Simon Ioannidis, John P. A. Kloda, Lorie A. McMillan, Dean Patten, Scott B. Shrier, Ian Ziegelstein, Roy C. Akena, Dickens H. Arroll, Bruce Ayalon, Liat Baradaran, Hamid R. Baron, Murray Bombardier, Charles H. Butterworth, Peter Carter, Gregory Chagas, Marcos H. Chan, Juliana C. N. Cholera, Rushina Conwell, Yeates de Manvan Ginkel, Janneke M. Fann, Jesse R. Fischer, Felix H. Fung, Daniel Gelaye, Bizu Goodyear-Smith, Felicity Greeno, Catherine G. Hall, Brian J. Harrison, Patricia A. Harter, Martin Hegerl, Ulrich Hides, Leanne Hobfoll, Stevan E. Hudson, Marie Hyphantis, Thomas Inagaki, Masatoshi Jette, Nathalie Khamseh, Mohammad E. Kiely, Kim M. Kwan, Yunxin Lamers, Femke Liu, Shen-Ing Lotrakul, Manote Loureiro, Sonia R. Lowe, Bernd McGuire, Anthony Mohd-Sidik, Sherina Munhoz, Tiago N. Muramatsu, Kumiko Osorio, Flavia L. Patel, Vikram Pence, Brian W. Persoons, Philippe Picardi, Angelo Reuter, Katrin Rooney, Alasdair G. Santos, Ina S. Shaaban, Juwita Sidebottom, Abbey Simning, Adam Stafford, Lesley Sung, Sharon Tan, Pei Lin Lynnette Turner, Alyna van Weert, Henk C. White, Jennifer Whooley, Mary A. Winkley, Kirsty Yamada, Mitsuhiko Benedetti, Andrea Thombs, Brett D. [a1]Lady Davis Institute for Medical Research Jewish General Hospital Montréal Québec Canada [a2]Department of Psychiatry McGill University Montréal Québec Canada [a3]Department of Epidemiology Biostatistics and Occupational Health McGill University Montréal Québec Canada [a4]Department of Psychology McGill University Montréal Québec Canada [a5]Schulich Library of Physical Sciences Life Sciences and Engineering McGill University Montreal Quebec Canada [a6]Department of Clinical Neuro and Developmental Psychology Amsterdam Public Health Research Institute Vrije Universiteit Amsterdam the Netherlands [a7]Hull York Medical School and the Department of Health Sciences University of York Heslington York UK [a8]Department of Medicine Department of Health Research and Policy Department of Biomedical Data Science Department of Statistics Stanford University Stanford California USA [a9]Library Concordia University Montréal Québec Canada [a10]Department of Community Health Sciences University of Calgary Calgary Alberta Canada [a11]Hotchkiss Brain Institute and O’Brien Institute for Public Health University of Calgary Calgary Alberta Canada [a12]Department of Medicine Johns Hopkins University School of Medicine Baltimore Maryland USA [a13]Department of Psychiatry Makerere University College of Health Sciences Kampala Uganda [a14]Department of General Practice and Primary Health Care University of Auckland Auckland New Zealand [a15]Louis and Gabi Weisfeld School of Social Work Bar Ilan University Ramat Gan Israel [a16]Endocrine Research Center Institute of Endocrinology and Metabolism Iran University of Medical Sciences Tehran Iran [a17]Ageing Clinical & Experimental Research Team Institute of Applied Health Sciences School of Medicine Medical Sciences and Nutrition University of Aberdeen Aberdeen Scotland UK [a18]Department of Medicine McGill University Montréal Québec Canada [a19]Department of Rehabilitation Medicine University of Washington S

BackgroundItem 9 of the Patient Health Questionnaire-9 (PHQ-9) queries about thoughts of death and self-harm, but not suicidality. Although it is sometimes used to assess suicide risk, most positive responses are not associated with suicidality. The PHQ-8, which omits Item 9, is thus increasingly used in research. We assessed equivalency of total score correlations and the diagnostic accuracy to detect major depression of the PHQ-8 and *** conducted an individual patient data meta-analysis. We fit bivariate random-effects models to assess diagnostic ***16 742 participants (2097 major depression cases) from 54 studies were included. The correlation between PHQ-8 and PHQ-9 scores was 0.996 (95% confidence interval 0.996 to 0.996). The standard cutoff score of 10 for the PHQ-9 maximized sensitivity + specificity for the PHQ-8 among studies that used a semi-structured diagnostic interview reference standard (N = 27). At cutoff 10, the PHQ-8 was less sensitive by 0.02 (−0.06 to 0.00) and more specific by 0.01 (0.00 to 0.01) among those studies (N = 27), with similar results for studies that used other types of interviews (N = 27). For all 54 primary studies combined, across all cutoffs, the PHQ-8 was less sensitive than the PHQ-9 by 0.00 to 0.05 (0.03 at cutoff 10), and specificity was within 0.01 for all cutoffs (0.00 to 0.01).ConclusionsPHQ-8 and PHQ-9 total scores were similar. Sensitivity may be minimally reduced with the PHQ-8, but specificity is similar.

关键词： Depression diagnostic accuracy individual participant data meta-analysis meta-analysis PHQ-8 PHQ-9 screening systematic review

Euclid preparation L. Calibration of the halo linear bias in Λ(ν)CDM cosmologies

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Castro, T. Fumagalli, A. Angulo, R.E. Bocquet, S. Borgani, S. Costanzi, M. Dakin, J. Dolag, K. Monaco, P. Saro, A. Sefusatti, E. Aghanim, N. Amendola, L. Andreon, S. Baccigalupi, C. Baldi, M. Bodendorf, C. Bonino, D. Branchini, E. Brescia, M. Caillat, A. Camera, S. Capobianco, V. Carbone, C. Carretero, J. Casas, S. Castellano, M. Castignani, G. Cavuoti, S. Cimatti, A. Colodro-Conde, C. Congedo, G. Conselice, C.J. Conversi, L. Copin, Y. Costille, A. Courbin, F. Courtois, H.M. Da Silva, A. Degaudenzi, H. De Lucia, G. Di Giorgio, A.M. Douspis, M. Dupac, X. Dusini, S. Farina, M. Farrens, S. Ferriol, S. Fosalba, P. Frailis, M. Franceschi, E. Fumana, M. Galeotta, S. Gillis, B. Giocoli, C. Gómez-Alvarez, P. Grazian, A. Grupp, F. Guzzo, L. Haugan, S.V.H. Holmes, W. Hormuth, F. Hornstrup, A. Ilić, S. Jahnke, K. Jhabvala, M. Joachimi, B. Keihänen, E. Kermiche, S. Kiessling, A. Kilbinger, M. Kubik, B. Kunz, M. Kurki-Suonio, H. Lilje, P.B. Lindholm, V. Lloro, I. Maiorano, E. Mansutti, O. Marggraf, O. Markovic, K. Martinelli, M. Martinet, N. Marulli, F. Massey, R. Maurogordato, S. Medinaceli, E. Melchior, M. Mellier, Y. Meneghetti, M. Merlin, E. Meylan, G. Moscardini, L. Munari, E. Niemi, S.-M. Padilla, C. Paltani, S. Pasian, F. Pedersen, K. Percival, W.J. Pettorino, V. Pires, S. Polenta, G. Poncet, M. Popa, L.A. Pozzetti, L. Raison, F. Renzi, A. Riccio, G. Romelli, E. Roncarelli, M. Saglia, R. Sakr, Z. Salvignol, J.-C. Sánchez, A.G. Sapone, D. Sartoris, B. Schirmer, M. Secroun, A. Serrano, S. Sirignano, C. Sirri, G. Stanco, L. Steinwagner, J. Tallada-Crespí, P. Taylor, A.N. Tereno, I. Toledo-Moreo, R. Torradeflot, F. Tutusaus, I. Valenziano, L. Vassallo, T. Kleijn, G. Verdoes Wang, Y. Weller, J. Zacchei, A. Zamorani, G. Zucca, E. Biviano, A. Bolzonella, M. Bozzo, E. Burigana, C. Calabrese, M. Di Ferdinando, D. Vigo, J.A. Escartin Finelli, F. Gracia-Carpio, J. Matthew, S. Mauri, N. Pezzotta, A. INAF-Osservatorio Astronomico di Trieste Via G. B. Tiepolo 11 Trieste34143 Italy INFN Sezione di Trieste Via Valerio 2 TS Trieste34127 Italy IFPU Institute for Fundamental Physics of the Universe via Beirut 2 Trieste34151 Italy ICSC - Centro Nazionale di Ricerca in High Performance Computing Big Data e Quantum Computing Via Magnanelli 2 Bologna Italy Ludwig-Maximilians-University Schellingstrasse 4 Munich80799 Germany Paseo Manuel de Lardizabal 4 Guipuzkoa Donostia-San Sebastián20018 Spain IKERBASQUE Basque Foundation for Science Bilbao48013 Spain Universitäts-Sternwarte München Fakultät für Physik Ludwig-Maximilians-Universität München Scheinerstrasse 1 München81679 Germany Dipartimento di Fisica - Sezione di Astronomia Università di Trieste Via Tiepolo 11 Trieste34131 Italy Department of Astrophysics University of Zurich Winterthurerstrasse 190 Zurich8057 Switzerland Université Paris-Saclay CNRS Institut d’astrophysique spatiale Orsay91405 France Institut für Theoretische Physik University of Heidelberg Philosophenweg 16 Heidelberg69120 Germany INAF-Osservatorio Astronomico di Brera Via Brera 28 Milano20122 Italy SISSA International School for Advanced Studies Via Bonomea 265 TS Trieste34136 Italy Dipartimento di Fisica e Astronomia Università di Bologna Via Gobetti 93/2 Bologna40129 Italy INAF-Osservatorio di Astrofisica e Scienza dello Spazio di Bologna Via Piero Gobetti 93/3 Bologna40129 Italy INFN-Sezione di Bologna Viale Berti Pichat 6/2 Bologna40127 Italy Max Planck Institute for Extraterrestrial Physics Giessenbachstr. 1 Garching85748 Germany Pino Torinese10025 Italy Dipartimento di Fisica Università di Genova Via Dodecaneso 33 Genova16146 Italy INFN-Sezione di Genova Via Dodecaneso 33 Genova16146 Italy Department of Physics "E. Pancini" University Federico II Via Cinthia 6 Napoli80126 Italy INAF-Osservatorio Astronomico di Capodimonte Via Moiariello 16 Napoli80131 Italy INFN section of Naples Vi

The Euclid mission, designed to map the geometry of the dark Universe, presents an unprecedented opportunity for advancing our understanding of the cosmos through its photometric galaxy cluster survey. Central to this endeavor is the accurate calibration of the mass- and redshift-dependent halo bias (HB), which is the focus of this paper. We enhance the precision of HB predictions, which is crucial for deriving cosmological constraints from the clustering of galaxy clusters. Our study is based on the peak-background split (PBS) model linked to the halo mass function (HMF), and extends it with a parametric correction to precisely align with results from an extended set of N-body simulations carried out with the OpenGADGET3 code. Employing simulations with fixed and paired initial conditions, we meticulously analyze the matter-halo cross-spectrum and model its covariance using a large number of mock catalogs generated with Lagrangian Perturbation Theory simulations with the PINOCCHIO code. This ensures a comprehensive understanding of the uncertainties in our HB calibration. Our findings indicate that the calibrated HB model is remarkably resilient against changes in cosmological parameters including those involving massive neutrinos. The robustness and adaptability of our calibrated HB model provide an important contribution to the cosmological exploitation of the cluster surveys to be provided by the Euclid mission. This study highlights the necessity of continuously refining the calibration of cosmological tools like the HB to match the advancing quality of observational data. As we project the impact of our calibrated model on cosmological constraints, we find that, given the sensitivity of the Euclid survey, a miscalibration of the HB could introduce biases in cluster cosmology analyses. Our work fills this critical gap, ensuring the HB calibration matches the expected precision of the Euclid survey. Copyright © 2024, The Authors. All rights reserved.

关键词： Cosmology

Learning analytics to improve writing skills for young children – an holistic approach

学校读者我要写书评

暂无评论

Journal of Research in Innovative Teaching and Learning 2017年第2期10卷 143-159页

作者： Steinhauer, Nina Gros, Michael Ebner, Martin Ebner, Markus Huppertz, Anneliese Cormann, Mike Biermeier, Susanne Burk, Lena Edtstadler, Konstanze Gabriel, Sonja Wintschnig, Martina Aspalter, Christian Martich, Susanne Landesinstitut für Pädagogik und Medien Saarbrücken Germany Department of Educational Technology Graz University of Technology Graz Austria Institute for Interactive Systems and Data Science Faculty of Computer Science and Biomedical Engineering Technische Universitat Graz Graz Austria School of Raeren Raeren Belgium Albert-Weisgerber School St Ingbert Germany Institute of Professionalisation in Early Childhood and Primary Teacher Education University College of Teacher Education Steiermark Graz Austria University College of Teacher Education Vienna/Krems Vienna Austria

Purpose: Due to the important role of orthography in society, the project called IDeRBlog presented in this paper created a web-based tool to motivate pupils to write text as well as to read and to comment on texts written by fellow students. In addition, IDeRBlog aims to improve student’s German orthography skills and supports teachers and parents with training materials for their students. The paper aims to discuss these issues. Design/methodology/approach: With the aid of learning analytics, the submitted text is analyzed and special feedback is given to the students so that they can try to correct the misspelled words themselves. The teachers as well as the parents are benefiting from the analysis and exercises suggested by the system. Findings: A recent study showed the efficiency of the system in form of an improvement of the students’ orthographic skills. Over a period of four months 70 percent of the students achieved a significant reduction of their spelling mistakes. Originality/value: IDeRBlog is an innovative approach to improving orthography skills combining blogging and new media with writing and practice. © 2017, Nina Steinhauer, Michael Gros, Martin Ebner, Markus Ebner, Anneliese Huppertz, Mike Cormann, Susanne Biermeier, Lena Burk, Konstanze Edtstadler, Sonja Gabriel, Martina Wintschnig, Christian Aspalter and Susanne Martich.

关键词： German orthography German spelling acquisition Learning analytics Technology enhanced learning