检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Chicharro, Daniel Panzeri, Stefano Shpitser, Ilya Neural Computation Laboratory Center for Neuroscience and Cognitive Systems@UniTn Istituto Italiano di Tecnologia Rovereto38068 Department of Neurobiology Harvard Medical School BostonMA02115 United States Department of Computer Science Whiting School of Engineering Johns Hopkins University

Constraint-based structure learning algorithms infer the causal structure of multi-variate systems from observational data by determining an equivalent class of causal structures compatible with the conditional independencies in the data. Methods based on additive-noise (AN) models have been proposed to further discriminate between causal structures that are equivalent in terms of conditional independencies. These methods rely on a particular form of the generative functional equations, with an additive noise structure, which allows inferring the directionality of causation by testing the independence between the residuals of a nonlinear regression and the predictors (nrr-independencies). Full causal structure identifiability has been proven for systems that contain only additive-noise equations and have no hidden variables. We extend the AN framework in several ways. We introduce alternative regression-free tests of independence based on conditional variances (cv-independencies). We consider conditionally-additive-noise (CAN) models, in which the equations may have the AN form only after conditioning. We exploit asymmetries in nrr-independencies or cv-independencies resulting from the CAN form to derive a criterion that infers the causal relation between a pair of variables in a multivariate system without any assumption about the form of the equations or the presence of hidden *** Codes 62-07 62-09 Copyright © 2019, The Authors. All rights reserved.

关键词： Equivalence classes

来源：评论

学校读者我要写书评

暂无评论

Automatic Extraction of Medication Mentions from Tweets-Overview of the BioCreative VII Shared Task 3 Competition

引用

Database : the journal of biological databases and curation 2023年第2023期2023卷 baac108页

作者： Davy Weissenbacher Karen O'Connor Siddharth Rawal Yu Zhang Richard Tzong-Han Tsai Timothy Miller Dongfang Xu Carol Anderson Bo Liu Qing Han Jinfeng Zhang Igor Kulev Berkay Köprü Raul Rodriguez-Esteban Elif Ozkirimli Ammer Ayach Roland Roller Stephen Piccolo Peijin Han V G Vinod Vydiswaran Ramya Tekumalla Juan M Banda Parsa Bagherzadeh Sabine Bergler João F Silva Tiago Almeida Paloma Martinez Renzo Rivera-Zavala Chen-Kai Wang Hong-Jie Dai Luis Alberto Robles Hernandez Graciela Gonzalez-Hernandez Department of Computational Biomedicine Cedars-Sinai Medical Center Los Angeles CA USA. DBEI The Perelman School of Medicine University of Pennsylvania Philadelphia PA USA. Department of Computer Science and Information Engineering National Central University No. 300 Zhongda Rd Zhongli District Taoyuan 320 Taiwan. IoX Center National Taiwan University Da'an District Section 4 Roosevelt Rd No. 1 Barry Lam Hall Taipei 106 Taiwan. Research Center for Humanities and Social Sciences Academia Sinica No. 128 Section 2 Academia Rd Nangang District Taipei 115 Taiwan. Computational Health Informatics Program Boston Children's Hospital Boston MA USA. Department of Pediatrics Harvard Medical School Boston MA USA. NVIDIA Santa Clara CA USA. Department of Statistics Florida State University Tallahassee FL USA. Data and Analytics Chapter F. Hoffmann-La Roche Ltd Switzerland. Pharmaceutical Research and Early Development Roche Innovation Center Basel Switzerland. Speech and Language Technology Lab DFKI Berlin Germany. Department of Biology Brigham Young University Provo UT USA. Department of Computational Medicine and Bioinformatics Medical School University of Michigan Ann Arbor MI USA. Department of Learning Health Sciences Medical School University of Michigan Ann Arbor MI USA. School of Information University of Michigan Ann Arbor MI USA. Department of Computer Science Georgia State University Atlanta GA USA. CLaC Labs Concordia University Montreal Canada. DETI Institute of Electronics and Informatics Engineering of Aveiro University of Aveiro Portugal. Department of Computation University of A Coruña Spain. Computer Science and Engineering Department Universidad Carlos III de Madrid Madrid Spain. Big Data Laboratory Chunghwa Telecom Laboratories Taoyuan Taiwan. Department of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan. Department of Electrical Engineering College of Electrical Engineering and Computer Sci

This study presents the outcomes of the shared task competition BioCreative VII (Task 3) focusing on the extraction of medication names from a Twitter user's publicly available tweets (the user's 'timeline'). In general, detecting health-related tweets is notoriously challenging for natural language processing tools. The main challenge, aside from the informality of the language used, is that people tweet about any and all topics, and most of their tweets are not related to health. Thus, finding those tweets in a user's timeline that mention specific health-related concepts such as medications requires addressing extreme imbalance. Task 3 called for detecting tweets in a user's timeline that mentions a medication name and, for each detected mention, extracting its span. The organizers made available a corpus consisting of 182 049 tweets publicly posted by 212 Twitter users with all medication mentions manually annotated. The corpus exhibits the natural distribution of positive tweets, with only 442 tweets (0.2%) mentioning a medication. This task was an opportunity for participants to evaluate methods that are robust to class imbalance beyond the simple lexical match. A total of 65 teams registered, and 16 teams submitted a system run. This study summarizes the corpus created by the organizers and the approaches taken by the participating teams for this challenge. The corpus is freely available at https://***/tasks/biocreative-vii/track-3/. The methods and the results of the competing systems are analyzed with a focus on the approaches taken for learning from class-imbalanced data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ADCMO: An Anomaly Detection Approach Based on Local Outlier Factor for Continuously Monitored Object

ADCMO: An Anomaly Detection Approach Based on Local Outlier ...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Shubin Su Limin Xiao Li Ruan Rongbin Xu Shupan Li Zhaokai Wang Qigong He Wei Li State Key Laboratory of Software Development Environment Beihang University School of Computer Science and Engineering Beihang University Beijing China School of Electronics and Information Engineering Beihang University Beijing China The Classified Information Carrier Safety Management Engineering Technology Research Center of Beijing Beijing Jinghang Computation and Communication Research Institute Beijing China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Since the existing works in data stream anomaly detection mainly locate abnormal objects from data sequences instead of detecting the abnormal state of a monitored object in real-time. And they need a set of empirical predefined thresholds, which may affect the flexibility of the detection models. These limitations make the existing solutions no longer suitable for the real-time detection of the changes in the status of the monitored object. In this paper, we propose a new Abnormal conditions Detection approach (ADCMO) on the Continuously Monitored Object. ADCMO incorporates the data distribution property to carry out the anomaly quantification for the data in the data stream, and then the abnormal conditions of the monitored object are quantified by the anomaly information of the current data and historical data. Finally, the anomaly state is adaptively determined by the distribution of anomaly coefficients. ADCMO can detect the changes in the status by calculating the outlier coefficient of the object at each moment and adaptively make the abnormal early warning. The experiments show that ADCMO can do this any-time, dynamically, efficiently and effectively.

关键词： Monitoring Biomedical monitoring Anomaly detection Real-time systems Transient analysis Laboratories Software

来源：评论

学校读者我要写书评

暂无评论

Robust classification with sparse representation fusion on diverse data subsets

arXiv

引用

arXiv 2019年

作者： Feng, Chun-Mei Xu, Yong Li, Zuoyong Yang, Jian Bio-Computing Research Center Harbin Institute of Technology Shenzhen Guangdong518055 China Key Laboratory of Network Oriented Intelligent Computation Shenzhen Guangdong518055 China Fuzhou350121 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing Jiangsu210094 China

Sparse Representation (SR) techniques encode the test samples into a sparse linear combination of all training samples and then classify the test samples into the class with the minimum residual. The classification of SR techniques depends on the representation capability on the test samples. However, most of these models view the representation problem of the test samples as a deterministic problem, ignoring the uncertainty of the representation. The uncertainty is caused by two factors, random noise in the samples and the intrinsic randomness of the sample set, which means that if we capture a group of samples, the obtained set of samples will be different in different conditions. In this paper, we propose a novel method based upon Collaborative Representation that is a special instance of SR and has closed-form solution. It performs Sparse Representation Fusion based on the Diverse Subset of training samples (SRFDS), which reduces the impact of randomness of the sample set and enhances the robustness of classification results. The proposed method is suitable for multiple types of data and has no requirement on the pattern type of the tasks. In addition, SRFDS not only preserves a closed-form solution but also greatly improves the classification performance. Promising results on various datasets serve as the evidence of better performance of SRFDS than other SR-based methods. The Matlab code of SRFDS will be accessible at http://***/***. Copyright © 2019, The Authors. All rights reserved.

关键词： Sampling

来源：评论

学校读者我要写书评

暂无评论

The association for the advancement of artificial intelligence 2020 workshop program

The association for the advancement of artificial intelligen...

引用

作者： Bang, Grace Barash, Guy Bea, Ryan Cali, Jacques Castillo-Effen, Mauricio Chen, Xin Cynthia Chhaya, Niyati Dhoopar, Rohan Dumancic, Sebastijan Espinoza, Huáscar Farchi, Eitan Fioretto, Ferdinando Fuentetaja, Raquel Galley, Michel Geib, Christopher Hernández-Orallo, José Huang, Xiaowei Keren, Sarah Kim, Seokhwan Jaidka, Kokil Liu, Xiaomo Lu, Tyler Ma, Zhiqiang Mallah, Richard McDermid, John Michalowski, Martin Mirsky, Reuth Héigeartaigh, Seán Ó. Ramachandran, Deepak Segovia-Aguas, Javier Shaban-Nejad, Arash Shehory, Onn Shwartz, Vered Srivastava, Siddharth Talamadupula, Kartik Tang, Jian Zhang, Dell Zhang, Jian S&P Global. Western Digital University of Southampton United Kingdom Blue Prism Group PLC Lockheed Martin's Advanced Technology Laboratories ArlingtonVA United States University of Hong Kong Hong Kong Adobe Research Google Research Katholieke Universiteit Leuven Belgium Commissariat à ĺÉnergie Atomique France IBM Research Department of Electrical Engineering and Computer Science Syracuse University United States Universidad Carlos III de Madrid Spain Microsoft Research AI SIFT LLC Universitat Politècnica de València Spain Leverhulme Centre for the Future of Intelligence United Kingdom Department of Computer Science University of Liverpool United Kingdom National University of Singapore Singapore Harvard School of Engineering and Applied Sciences in the of Fields of Multiagent Environment Design and Goal Recognition Design Amazon Alexa AI Future of Life Institute United States University of York Assuring Autonomy International Program United Kingdom University of Minnesota School of Nursing MinneapolisMN United States University of Texas at Austin AustinTX United States Institut de Robòtica i Informàtica Industrial Spanish Council for Scientific Research Technical University of Catalonia Spain Oak Ridge National Laboratory Center for Biomedical Informatics Department of Pediatrics University of Tennessee Health Science Center United States Bar Ilan University Israel University of Washington SeattleWA United States Autonomous Agents and Intelligent Robots lab of the School of Computing Informatics Decision Systems Arizona State University United States DiDi AI Labs School of Industrial and System Engineering Georgia Institute of Technology United States University of London United Kingdom Microsoft Azure

The Association for the Advancement of Artificial Intelligence 2020 Workshop Program included twenty-three workshops covering a wide range of topics in artificial intelligence. This report contains the required reports, which were submitted by most, but not all, of the workshop chairs. Copyright © 2020, Association for the Advancement of Artificial Intelligence. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Slope selection in unstable multilayer growth in 1+1 dimensions: Step flow models with downward funneling

引用

Physical Review E 2019年第5期100卷 052802-052802页

作者： Ian Johnson Christian Ratsch Frederic Gibou Dionisios Margetis Department of Mathematics University of Maryland College Park Maryland 20742 USA. Institute for Pure and Applied Mathematics and Department of Mathematics University of California Los Angeles California 90095 USA. Department of Mechanical Engineering Department of Computer Science and Department of Mathematics University of California Santa Barbara California 93106 USA. Institute for Physical Science and Technology Department of Mathematics and Center for Scientific Computation and Mathematical Modeling University of Maryland College Park Maryland 20742 USA.

We study analytically and numerically aspects of the dynamics of slope selection for one-dimensional models describing the motion of line defects, steps, in homoepitaxial crystal growth. The kinetic processes include diffusion of adsorbed atoms (adatoms) on terraces, attachment and detachment of atoms at steps with large yet finite, positive Ehrlich-Schwoebel step-edge barriers, material deposition on the surface from above, and the mechanism of downward funneling (DF) via a phenomenological parameter. In this context, we account for the influence of boundary conditions at extremal steps on the dynamics of slope selection. Furthermore, we consider the effect of repulsive, nearest-neighbor force-dipole step-step interactions. For geometries with straight steps, we carry out numerical simulations of step flow, which demonstrate that slope selection eventually occurs. We apply perturbation theory to characterize time-periodic solutions of step flow for slope-selected profiles. By this method, we show how a simplified step flow theory with constant probabilities for the motion of deposited atoms can serve as an effective model of slope selection in the presence of DF. Our analytical findings compare favorably to step simulations.

关键词： Growth Interface & surface thermodynamics Surface & interfacial phenomena Surface diffusion Surface instabilities

来源：评论

学校读者我要写书评

暂无评论

Enhancing MPPT performance for partially shaded photovoltaic arrays through backstepping control with Genetic Algorithm-optimized gains

引用

scientific reports 2024年第1期14卷 3334页

作者： Serge Raoul Dzonde Naoussi Kenfack Tsobze Saatong Reagan Jean Jacques Molu Wulfran Fendzi Mbasso Mohit Bajaj Mohamed Louzazni Milkias Berhanu Salah Kamel Technology and Applied Sciences Laboratory U.I.T. of Douala University of Douala P.O. Box 8689 Douala Cameroon. Unité de Recherche d'Automatique et d'Informatique Appliquée I.U.T. Fotso Victor University of Dschang P.O. Box 134 Bandjoun Cameroon. Department of Electrical Engineering Graphic Era (Deemed to be University) Dehra Dun 248002 India. mb.czechia@***. Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan. mb.czechia@***. Graphic Era Hill University Dehra Dun 248002 India. mb.czechia@***. Applied Science Research Center Applied Science Private University Amman 11937 Jordan. mb.czechia@***. Science Engineer Laboratory for Energy LabSIPE National School of Applied Sciences ENSAJ Chouaib Doukkali University 24000 El Jadida Morocco. Department of Electrical and Computer Engineering Addis Ababa Science and Technology University Adama Ethiopia. mil_ber2000@astu.edu.et. Department of Electrical Engineering Faculty of Engineering Aswan University Aswân 81542 Egypt.

As the significance and complexity of solar panel performance, particularly at their maximum power point (MPP), continue to grow, there is a demand for improved monitoring systems. The presence of variable weather conditions in Maroua, including potential partial shadowing caused by cloud cover or urban buildings, poses challenges to the efficiency of solar systems. This study introduces a new approach to tracking the Global Maximum Power Point (GMPP) in photovoltaic systems within the context of solar research conducted in Cameroon. The system utilizes Genetic Algorithm (GA) and Backstepping Controller (BSC) methodologies. The Backstepping Controller (BSC) dynamically adjusts the duty cycle of the Single Ended Primary Inductor Converter (SEPIC) to align with the reference voltage of the Genetic Algorithm (GA) in Maroua's dynamic environment. This environment, characterized by intermittent sunlight and the impact of local factors and urban shadowing, affects the production of energy. The Genetic Algorithm is employed to enhance the efficiency of BSC gains in Maroua's solar environment. This optimization technique expedites the tracking process and minimizes oscillations in the GMPP. The adaptability of the learning algorithm to specific conditions improves energy generation, even in the challenging environment of Maroua. This study introduces a novel approach to enhance the efficiency of photovoltaic systems in Maroua, Cameroon, by tailoring them to the specific solar dynamics of the region. In terms of performance, our approach surpasses the INC-BSC, P&O-BSC, GA-BSC, and PSO-BSC methodologies. In practice, the stabilization period following shadowing typically requires fewer than three iterations. Additionally, our Maximum Power Point Tracking (MPPT) technology is based on the Global Maximum Power Point (GMPP) methodology, contrasting with alternative technologies that prioritize the Local Maximum Power Point (LMPP). This differentiation is particularly relevant in

关键词： Backstepping controller Genetic algorithm Maximum power point tracking Partial shading effects Photovoltaic array

来源：评论

学校读者我要写书评

暂无评论

Exploiting function words feature in classifying deceptive and truthful reviews 13

Exploiting function words feature in classifying deceptive a...

引用

13th International Conference on Digital Information Management, ICDIM 2018

作者： Siagian, Al Hafiz Akbar Maulana Aritsugi, Masayoshi Computer Science and Electrical Engineering Graduate School of Science and Technology Kumamoto University Kumamoto Japan Big Data Science and Technology Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan Center for Scientific Documentation and Information Indonesian Institute of Sciences Jakarta Indonesia

ISBN: (纸本)9781538652435

In this paper, we exploit function words as a feature for classifying deceptive and truthful opinions in the online reviews. Initially, we employ function words as a single feature to classify deceptive and truthful reviews. Then, we combine those function words with widely used text features in this task, namely, word and character n-grams, as our proposed combination feature. The experimental results exhibit that our proposed feature could perform well in this deceptive and truthful reviews classification. In particular, the obtained results of our proposed combination feature could outperform those using the baseline feature, i.e., word and character n-grams combinations. In addition, we apply the feature attribute selection, that is, Information Gain in conjunction with Ranker of WEKA, on our proposed combination feature. This treatment is to examine further the robustness of our proposed combination feature when dealing with this task. The latter experiment shows that after applying the feature attribute selection, our proposed combination feature was able to increase the classification results. © 2018 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Measurement and interpretation of same-sign W boson pair production in association with two jets in pp collisions at (Formula presented.) TeV with the ATLAS detector

引用

Journal of High Energy Physics 2024年第4期2024卷 1-61页

作者： Aad, G. Abbott, B. Abeling, K. Abicht, N.J. Abidi, S.H. Aboulhorma, A. Abramowicz, H. Abreu, H. Abulaiti, Y. Abusleme Hoffman, A.C. Acharya, B.S. Adam Bourdarios, C. Adamczyk, L. Adamek, L. Addepalli, S.V. Addison, M.J. Adelman, J. Adiguzel, A. Adye, T. Affolder, A.A. Afik, Y. Agaras, M.N. Agarwala, J. Aggarwal, A. Agheorghiesei, C. Ahmad, A. Ahmadov, F. Ahmed, W.S. Ahuja, S. Ai, X. Aielli, G. Aikot, A. Ait Tamlihat, M. Aitbenchikh, B. Aizenberg, I. Akbiyik, M. Åkesson, T.P.A. Akimov, A.V. Akiyama, D. Akolkar, N.N. Al Khoury, K. Alberghi, G.L. Albert, J. Albicocco, P. Albouy, G.L. Alderweireldt, S. Aleksa, M. Aleksandrov, I.N. Alexa, C. Alexopoulos, T. Alfonsi, F. Algren, M. Alhroob, M. Ali, B. Ali, H.M.J. Ali, S. Alibocus, S.W. Aliev, M. Alimonti, G. Alkakhi, W. Allaire, C. Allbrooke, B.M.M. Allen, J.F. Allendes Flores, C.A. Allport, P.P. Aloisio, A. Alonso, F. Alpigiani, C. Alvarez Estevez, M. Alvarez Fernandez, A. Alves Cardoso, M. Alviggi, M.G. Aly, M. Amaral Coutinho, Y. Ambler, A. Amelung, C. Amerl, M. Ames, C.G. Amidei, D. Amor Dos Santos, S.P. Amos, K.R. Ananiev, V. Anastopoulos, C. Andeen, T. Anders, J.K. Andrean, S.Y. Andreazza, A. Angelidakis, S. Angerami, A. Anisenkov, A.V. Annovi, A. Antel, C. Anthony, M.T. Antipov, E. Antonelli, M. Anulli, F. Aoki, M. Aoki, T. Aparisi Pozo, J.A. Aparo, M.A. Aperio Bella, L. Appelt, C. Apyan, A. Aranzabal, N. Arcangeletti, C. Arce, A.T.H. Arena, E. Arguin, J.-F. Argyropoulos, S. Arling, J.-H. Arnaez, O. Arnold, H. Artoni, G. Asada, H. Asai, K. Asai, S. Asbah, N.A. Assamagan, K. Astalos, R. Atashi, S. Atkin, R.J. Atkinson, M. Atmani, H. Atmasiddha, P.A. Augsten, K. Auricchio, S. Auriol, A.D. Austrup, V.A. Avolio, G. Axiotis, K. Azuelos, G. Babal, D. Bachacou, H. Bachas, K. Bachiu, A. Backman, F. Badea, A. Bagnaia, P. Bahmani, M. Bailey, A.J. Bailey, V.R. Baines, J.T. Baines, L. Bakalis, C. Baker, O.K. Bakos, E. Bakshi Gupta, D. Balakrishnan, V. Balasubramanian, R. Baldin, E.M. Balek, P. Ballabene, E. Balli, F. Baltes, L.M. Balunas, W.K. Balz, J. Banas, E. Bandieramont Department of Physics University of Adelaide Department of Physics University of Alberta Department of Physics Ankara University Division of Physics TOBB University of Economics and Technology LAPP Université Savoie Mont Blanc CNRS/IN2P3 APC Université Paris Cité CNRS/IN2P3 High Energy Physics Division Argonne National Laboratory Department of Physics University of Arizona Department of Physics University of Texas at Arlington Physics Department National and Kapodistrian University of Athens Physics Department National Technical University of Athens Department of Physics University of Texas at Austin Institute of Physics Azerbaijan Academy of Sciences Institut de Física d’Altes Energies (IFAE) Barcelona Institute of Science and Technology Institute of High Energy Physics Chinese Academy of Sciences Physics Department Tsinghua University Department of Physics Nanjing University School of Science Shenzhen Campus of Sun Yat-sen University University of Chinese Academy of Science (UCAS) Institute of Physics University of Belgrade Department for Physics and Technology University of Bergen Physics Division Lawrence Berkeley National Laboratory University of California Institut für Physik Humboldt Universität zu Berlin Albert Einstein Center for Fundamental Physics and Laboratory for High Energy Physics University of Bern School of Physics and Astronomy University of Birmingham Department of Physics Bogazici University Department of Physics Engineering Gaziantep University Department of Physics Istanbul University Facultad de Ciencias y Centro de Investigaciónes Universidad Antonio Nariño Departamento de Física Universidad Nacional de Colombia Dipartimento di Fisica e Astronomia A. Righi Università di Bologna INFN Sezione di Bologna Physikalisches Institut Universität Bonn Department of Physics Boston University Department of Physics Brandeis University Transilvania University of Brasov Horia Hulubei National Institute of Physics and Nuclear Engineering Department of Physics Alexandru

This paper presents the measurement of fiducial and differential cross sections for both the inclusive and electroweak production of a same-sign W-boson pair in association with two jets (W^±W^±jj) using 139 fb⁻¹ of proton-proton collision data recorded at a centre-of-mass energy of s = 13 TeV by the ATLAS detector at the Large Hadron Collider. The analysis is performed by selecting two same-charge leptons, electron or muon, and at least two jets with large invariant mass and a large rapidity difference. The measured fiducial cross sections for electroweak and inclusive W^±W^±jj production are 2.92 ± 0.22 (stat.) ± 0.19 (syst.) fb and 3.38 ± 0.22 (stat.) ± 0.19 (syst.) fb, respectively, in agreement with Standard Model predictions. The measurements are used to constrain anomalous quartic gauge couplings by extracting 95% confidence level intervals on dimension-8 operators. A search for doubly charged Higgs bosons H^±± that are produced in vector-boson fusion processes and decay into a same-sign W boson pair is performed. The largest deviation from the Standard Model occurs for an H^±± mass near 450 GeV, with a global significance of 2.5 standard deviations. © The Author(s) 2024.

关键词： Hadron-Hadron Scattering Vector Boson Production

来源：评论

学校读者我要写书评

暂无评论

Large language models surpass human experts in predicting neuroscience results

arXiv

引用

arXiv 2024年

作者： Luo, Xiaoliang Rechardt, Akilles Sun, Guangzhi Nejad, Kevin K. Yáñez, Felipe Yilmaz, Bati Lee, Kangjoo Cohen, Alexandra O. Borghesani, Valentina Pashkov, Anton Marinazzo, Daniele Nicholas, Jonathan Salatiello, Alessandro Sucholutsky, Ilia Minervini, Pasquale Razavi, Sepehr Rocca, Roberta Yusifov, Elkhan Okalova, Tereza Gu, Nianlong Ferianc, Martin Khona, Mikail Patil, Kaustubh R. Lee, Pui-Shee Mata, Rui Myers, Nicholas E. Bizley, Jennifer K. Musslick, Sebastian Bilgin, Isil Poyraz Niso, Guiomar Ales, Justin M. Gaebler, Michael Murty, N. Apurva Ratan Loued-Khenissi, Leyla Behler, Anna Hall, Chloe M. Dafflon, Jessica Bao, Sherry Dongqi Love, Bradley C. Department of Experimental Psychology University College London London United Kingdom Department of Engineering University of Cambridge Cambridge United Kingdom Department of Physiology Anatomy & Genetics University of Oxford Oxford United Kingdom Max Planck Institute for Neurobiology of Behavior – caesar Bonn Germany Bilkent University Ankara Turkey Department of Computer Science University of Bristol Bristol United Kingdom The Alan Turing Institute London United Kingdom Department of Psychiatry Yale University New Haven United States Psychology Emory University Atlanta United States Faculty of Psychology and Educational Sciences Université de Genève Genève Switzerland Neurosurgery Novosibirsk State Medical University Novosibirsk Russia Federal Center of Neurosurgery FSBI Novosibirsk Russia Department of Data Collection and Processing Systems Novosibirsk State Technical University Novosibirsk Russia Department of Data Analysis Ghent University Ghent Belgium Psychology New York University New York United States Department of Cognitive Neurology University of Tübingen Tübingen Germany Computer Science Princeton University Princeton United States ILCC University of Edinburgh Edinburgh United Kingdom Philosophy Psychology and Language Sciences The University of Edinburgh Edinburgh United Kingdom Department of Culture Cognition and Computation Aarhus University Aarhus Denmark Department of Molecular Life Sciences University of Zurich Zurich Switzerland Bioengineering University of Pennsylvania Philadelphia United States Linguistic Research Infrastructure University of Zurich Zurich Switzerland Electronic and Electrical Engineering University College London London United Kingdom Brain and Cognitive Sciences Massachusetts Institute of Technology CambridgeMA United States Institute of Neuroscience and Medicine INM-7: Brain and Behaviour Research Centre Jülich Jülich Germany Medical Faculty Institute of Systems Neuroscience Heinrich Hein

scientific discoveries often hinge on synthesizing decades of research, a task that potentially outstrips human information processing capacities. Large language models (LLMs) offer a solution. LLMs trained on the vast scientific literature could potentially integrate noisy yet interrelated findings to forecast novel results better than human experts. To evaluate this possibility, we created BrainBench, a forward-looking benchmark for predicting neuroscience results. We find that LLMs surpass experts in predicting experimental outcomes. BrainGPT, an LLM we tuned on the neuroscience literature, performed better yet. Like human experts, when LLMs were confident in their predictions, they were more likely to be correct, which presages a future where humans and LLMs team together to make discoveries. Our approach is not neuroscience-specific and is transferable to other knowledge-intensive endeavors. © 2024, CC BY.

关键词： Prediction models

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：