检索结果-内蒙古大学图书馆

Emergent communication through negotiation 6

学校读者我要写书评

暂无评论

Emergent communication through negotiation

6th International Conference on Learning Representations, ICLR 2018

作者： Cao, Kris Lazaridou, Angeliki Lanctot, Marc Leibo, Joel Z. Tuyls, Karl Clark, Stephen Department of Computer Science and Technology University of Cambridge United Kingdom DeepMind London United Kingdom

Multi-agent reinforcement learning offers a way to study how communication could emerge in communities of agents needing to solve specific problems. In this paper, we study the emergence of communication in the negotiation environment, a semi-cooperative model of agent interaction. We introduce two communication protocols – one grounded in the semantics of the game, and one which is a priori ungrounded and is a form of cheap talk. We show that self-interested agents can use the pre-grounded communication channel to negotiate fairly, but are unable to effectively use the ungrounded channel. However, prosocial agents do learn to use cheap talk to find an optimal negotiating strategy, suggesting that cooperation is necessary for language to emerge. We also study communication behaviour in a setting where one agent interacts with agents in a community with different levels of prosociality and show how agent identifiability can aid negotiation. © Learning Representations, ICLR 2018 - Conference Track *** right reserved.

关键词： Semantics

Efficient product formulas for commutators and applications to quantum simulation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Yu-An Childs, Andrew M. Hafezi, Mohammad Jiang, Zhang Kim, Hwanmun Xu, Yijia Google Quantum AI 340 Main Street VeniceCA90291 United States Department of Physics Joint Quantum Institute NIST University of Maryland College ParkMD20742 United States Condensed Matter Theory Center University of Maryland College ParkMD20472 United States Joint Center for Quantum Information and Computer Science University of Maryland College ParkMD20742 United States Department of Computer Science University of Maryland College ParkMD20742 United States Institute for Advanced Computer Studies University of Maryland College ParkMD20742 United States Department of Electrical and Computer Engineering Institute for Research in Electronics and Applied Physics University of Maryland College ParkMD20742 United States Institute for Physical Science and Technology University of Maryland College ParkMD20742 United States

We construct product formulas for exponentials of commutators and explore their applications. First, we directly construct a third-order product formula with six exponentials by solving polynomial equations obtained using the operator differential method. We then derive higher-order product formulas recursively from the third-order formula. We improve over previous recursive constructions, reducing the number of gates required to achieve the same accuracy. In addition, we demonstrate that the constituent linear terms in the commutator can be included at no extra cost. As an application, we show how to use the product formulas in a digital protocol for counterdiabatic driving, which increases the fidelity for quantum state preparation. We also discuss applications to quantum simulation of one-dimensional fermion chains with nearest- and next-nearest-neighbor hopping terms, and two-dimensional fractional quantum Hall phases. Copyright © 2021, The Authors. All rights reserved.

关键词： Quantum chemistry

How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bunne, Charlotte Roohani, Yusuf Rosen, Yanay Gupta, Ankit Zhang, Xikun Roed, Marcel Alexandrov, Theo AlQuraishi, Mohammed Brennan, Patricia Burkhardt, Daniel B. Califano, Andrea Cool, Jonah Dernburg, Abby F. Ewing, Kirsty Fox, Emily B. Haury, Matthias Herr, Amy E. Horvitz, Eric Hsu, Patrick D. Jain, Viren Johnson, Gregory R. Kalil, Thomas Kelley, David R. Kelley, Shana O. Kreshuk, Anna Mitchison, Tim Otte, Stephani Shendure, Jay Sofroniew, Nicholas J. Theis, Fabian Theodoris, Christina V. Upadhyayula, Srigokul Valer, Marc Wang, Bo Xing, Eric Yeung-Levy, Serena Zitnik, Marinka Karaletsos, Theofanis Regev, Aviv Lundberg, Emma Leskovec, Jure Quake, Stephen R. Department of Computer Science Stanford University StanfordCA United States Genentech South San FranciscoCA United States Chan Zuckerberg Initiative Redwood CityCA United States School of Computer and Communication Sciences School of Life Sciences EPFL Lausanne Switzerland Arc Institute Palo AltoCA United States KTH Royal Institute of Technology Science for Life Laboratory Department of Protein Science Stockholm Sweden Department of Bioengineering Stanford University StanfordCA United States Department of Pharmacology University of California San DiegoCA United States Department of Bioengineering University of California San DiegoCA United States Department of Systems Biology Columbia University New YorkNY United States Cellarity SomervilleMA United States Vagelos College of Physicians and Surgeons Columbia University Irving Medical Center New YorkNY United States Chan Zuckerberg Biohub New YorkNY United States Department of Molecular and Cell Biology University of California Berkeley BerkeleyCA United States Department of Statistics Stanford University StanfordCA United States Chan Zuckerberg Biohub San Francisco CA United States Chan Zuckerberg Institute for Advanced Biological Imaging Redwood CityCA United States Department of Bioengineering University of California BerkeleyCA United States Microsoft Research RedmondWA United States Center for Computational Biology University of California Berkeley BerkeleyCA United States Google Research Mountain ViewCA United States NewLimit San FranciscoCA United States Schmidt city United States Calico Life Sciences LLC San FranciscoCA United States Chan Zuckerberg Biohub Chicago IL United States Northwestern University EvanstonIL United States Cell Biology and Biophysics Unit European Molecular Biology Laboratory Heidelberg Germany Department of Systems Biology Harvard Medical School BostonMA United States Department of Genome Sciences University of Washington SeattleWA Unit

The cell is arguably the most fundamental unit of life and is central to understanding biology. Accurate modeling of cells is important for this understanding as well as for determining the root causes of disease. Recent advances in artificial intelligence (AI), combined with the ability to generate large-scale experimental data, present novel opportunities to model cells. Here we propose a vision of leveraging advances in AI to construct virtual cells, high-fidelity simulations of cells and cellular systems under different conditions that are directly learned from biological data across measurements and scales. We discuss desired capabilities of such AI Virtual Cells, including generating universal representations of biological entities across scales, and facilitating interpretable in silico experiments to predict and understand their behavior using Virtual Instruments. We further address the challenges, opportunities and requirements to realize this vision including data needs, evaluation strategies, and community standards and engagement to ensure biological accuracy and broad utility. We envision a future where AI Virtual Cells help identify new drug targets, predict cellular responses to perturbations, as well as scale hypothesis exploration. With open science collaborations across the biomedical ecosystem that includes academia, philanthropy, and the biopharma and AI industries, a comprehensive predictive understanding of cell mechanisms and interactions has come into reach. © 2024, CC BY.

关键词： Virtual environments

LOCALIZATION with LIMITED ANNOTATION for CHEST X-RAYS

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Rozenberg, Eyal Freedman, Daniel Bronstein, Alex Department of Computer Science Technion - Israel Institute of Technology Haifa Israel Google Research Haifa Israel

Localization of an object within an image is a common task in medical imaging. Learning to localize or detect objects typically requires the collection of data that has been labelled with bounding boxes or similar annotations, which can be very time consuming and expensive. A technique that could perform such learning with much less annotation would, therefore, be quite valuable. We present such a technique for localization with limited annotation, in which the number of images with bounding boxes can be a small fraction of the total dataset (e.g. less than 1%);all other images only possess a whole image label and no bounding box. We propose a novel loss function for tackling this problem;the loss is a continuous relaxation of a well-defined discrete formulation of weakly supervised learning and is numerically well-posed. Furthermore, we propose a new architecture which accounts for both patch dependence and shift-invariance, through the inclusion of CRF layers and anti-aliasing filters, respectively. We apply our technique to the localization of thoracic diseases in chest X-ray images and demonstrate state-of-the-art localization performance on the ChestX-ray14 dataset [1]. © 2019, CC BY-NC-SA.

关键词： Object detection

Higher-order comparisons of sentence encoder representations

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Abdou, Mostafa Kulmizev, Artur Hill, Felix Low, Daniel M. Søgaard, Anders Department of Computer Science University of Copenhagen Department of Linguistics and Philology Uppsala University DeepMind Program in Speech and Hearing Bioscience and Technology Harvard Medical School-MIT

Representational Similarity Analysis (RSA) is a technique developed by neuroscientists for comparing activity patterns of different measurement modalities (e.g., fMRI, electrophysiology, behavior). As a framework, RSA has several advantages over existing approaches to interpretation of language encoders based on probing or diagnostic classification: namely, it does not require large training samples, is not prone to overfitting, and it enables a more transparent comparison between the representational geometries of different models and modalities. We demonstrate the utility of RSA by establishing a previously unknown correspondence between widely-employed pretrained language encoders and human processing difficulty via eye-tracking data, showcasing its potential in the interpretability toolbox for neural models. Copyright © 2019, The Authors. All rights reserved.

关键词： Signal encoding

Predicting Origin-Destination Flow via Multi-Perspective Graph Convolutional Network

学校读者我要写书评

暂无评论

Predicting Origin-Destination Flow via Multi-Perspective Gra...

International Conference on Data Engineering

作者： Hongzhi Shi Quanming Yao Qi Guo Yaguang Li Lingyu Zhang Jieping Ye Yong Li Yan Liu Beijing National Research Center for Information Science and Technology (BNRist) Department of Electronic Engineering Tsinghua University Beijing China 4 Paradigm Inc. Hong Kong China College of Computer Science Sichuan University Chengdu China Google Inc. Mountain View United States AI Labs Didi Chuxing Beijing China Department of Computer Science University of Southern California Los Angeles United States

ISBN: (数字)9781728129037

ISBN: (纸本)9781728129044

Predicting Origin-Destination (OD) flow is a crucial problem for intelligent transportation. However, it is extremely challenging because of three reasons: first, correlations exist between both origins and destinations; second, the correlations are dynamic across the time; at last, there are multiple correlations from different aspects. To the best of our knowledge, existing models for OD flow prediction cannot tackle all of these three issues simultaneously. We propose Multi-Perspective Graph Convolutional Networks (MPGCN) to capture the complex dependencies. Our proposed model first utilizes long short-term memory (LSTM) network to extract temporal features for each OD pair and then learns the spatial dependency of origins and destinations by a two-dimensional graph convolutional network. Furthermore, we design a dynamic graph together with two static graphs to capture the complicated spatial dependencies and use an average strategy to obtain the final predicted OD flow. We conduct extensive experiments on two large-scale and real-world datasets, which not only demonstrate our design philosophy but also validate the effectiveness of the proposed model.

关键词： Correlation Feature extraction Predictive models Tensile stress Two dimensional displays Convolution Transportation

Information Scrambling in Computationally Complex Quantum Circuits

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Mi, Xiao Roushan, Pedram Quintana, Chris Mandrà, Salvatore Marshall, Jeffrey Neill, Charles Arute, Frank Arya, Kunal Atalaya, Juan Babbush, Ryan Bardin, Joseph C. Barends, Rami Bengtsson, Andreas Boixo, Sergio Bourassa, Alexandre Broughton, Michael Buckley, Bob B. Buell, David A. Burkett, Brian Bushnell, Nicholas Chen, Zijun Chiaro, Benjamin Collins, Roberto Courtney, William Demura, Sean Derk, Alan R. Dunsworth, Andrew Eppens, Daniel Erickson, Catherine Farhi, Edward Fowler, Austin G. Foxen, Brooks Gidney, Craig Giustina, Marissa Gross, Jonathan A. Harrigan, Matthew P. Harrington, Sean D. Hilton, Jeremy Ho, Alan Hong, Sabrina Huang, Trent Huggins, William J. Ioffe, L.B. Isakov, Sergei V. Jeffrey, Evan Jiang, Zhang Jones, Cody Kafri, Dvir Kelly, Julian Kim, Seon Kitaev, Alexei Klimov, Paul V. Korotkov, Alexander N. Kostritsa, Fedor Landhuis, David Laptev, Pavel Lucero, Erik Martin, Orion McClean, Jarrod R. McCourt, Trevor McEwen, Matt Megrant, Anthony Miao, Kevin C. Mohseni, Masoud Mruczkiewicz, Wojciech Mutus, Josh Naaman, Ofer Neeley, Matthew Newman, Michael Niu, Murphy Yuezhen O’Brien, Thomas E. Opremcak, Alex Ostby, Eric Pato, Balint Petukhov, Andre Redd, Nicholas Rubin, Nicholas C. Sank, Daniel Satzinger, Kevin J. Shvarts, Vladimir Strain, Doug Szalay, Marco Trevithick, Matthew D. Villalonga, Benjamin White, Theodore Yao, Z. Jamie Yeh, Ping Zalcman, Adam Neven, Hartmut Aleiner, Igor Kechedzhi, Kostyantyn Smelyanskiy, Vadim Chen, Yu Google Research United States QuAIL NASA Ames Research Center Moffett FieldCA94035 United States KBR Inc. 601 Jefferson St. HoustonTX77002 United States USRA Research Institute for Advanced Computer Science Mountain ViewCA94043 United States Department of Electrical and Computer Engineering University of Massachusetts AmherstMA United States Pritzker School of Molecular Engineering University of Chicago ChicagoIL United States California Institute of Technology PasadenaCA91125 United States Department of Electrical and Computer Engineering University of California RiversideCA United States Department of Physics University of California Santa BarbaraCA United States

Interaction in quantum systems can spread initially localized quantum information into the many degrees of freedom of the entire system. Understanding this process, known as quantum scrambling, is the key to resolving various conundrums in physics. Here, by measuring the time-dependent evolution and fluctuation of out-of-time-order correlators, we experimentally investigate the dynamics of quantum scrambling on a 53-qubit quantum processor. We engineer quantum circuits that distinguish the two mechanisms associated with quantum scrambling, operator spreading and operator entanglement, and experimentally observe their respective signatures. We show that while operator spreading is captured by an efficient classical model, operator entanglement requires exponentially scaled computational resources to simulate. These results open the path to studying complex and practically relevant physical observables with near-term quantum processors. © 2021, CC BY.

关键词： Quantum optics

Large-Scale, Real-Time Visual-Inertial localization revisited

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Lynen, Simon Zeisl, Bernhard Aiger, Dror Bosse, Michael Hesch, Joel Pollefeys, Marc Siegwart, Roland Sattler, Torsten Google Switzerland Zurich Switzerland Google Israel Tel Aviv Israel Autonomous Systems Lab ETH Zurich Computer Vision and Geometry Group Department of Computer Science ETH Zurich Department of Microsoft Department of Electrical Engineering Chalmers University of Technology

The overarching goals in image-based localization are scale, robustness and speed. In recent years, approaches based on local features and sparse 3D point-cloud models have both dominated the benchmarks and seen successful realworld deployment. They enable applications ranging from robot navigation, autonomous driving, virtual and augmented reality to device geo-localization. Recently end-to-end learned localization approaches have been proposed which show promising results on small scale datasets. However the positioning accuracy, scalability, latency and compute & storage requirements of these approaches remain open challenges. We aim to deploy localization at global-scale where one thus relies on methods using local features and sparse 3D models. Our approach spans from offline model building to real-time client-side pose fusion. The system compresses appearance and geometry of the scene for efficient model storage and lookup leading to scalability beyond what what has been previously demonstrated. It allows for low-latency localization queries and efficient fusion run in real-time on mobile platforms by combining server-side localization with real-time visual-inertial-based camera pose tracking. In order to further improve efficiency we leverage a combination of priors, nearest neighbor search, geometric match culling and a cascaded pose candidate refinement step. This combination outperforms previous approaches when working with large scale models and allows deployment at unprecedented scale. We demonstrate the effectiveness of our approach on a proof-of-concept system localizing 2.5 million images against models from four cities in different regions on the world achieving query latencies in the 200ms range. Copyright © 2019, The Authors. All rights reserved.

关键词： Nearest neighbor search

Understanding metric-related pitfalls in image analysis validation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Reinke, Annika Tizabi, Minu D. Baumgartner, Michael Eisenmann, Matthias Heckmann-Nötzel, Doreen Kavur, A. Emre Rädsch, Tim Sudre, Carole H. Acion, Laura Antonelli, Michela Arbel, Tal Bakas, Spyridon Benis, Arriel Blaschko, Matthew B. Buettner, Florian Cardoso, M. Jorge Cheplygina, Veronika Chen, Jianxu Christodoulou, Evangelia Cimini, Beth A. Collins, Gary S. Farahani, Keyvan Ferrer, Luciana Galdran, Adrian van Ginneken, Bram Glocker, Ben Godau, Patrick Haase, Robert Hashimoto, Daniel A. Hoffman, Michael M. Huisman, Merel Isensee, Fabian Jannin, Pierre Kahn, Charles E. Kainmueller, Dagmar Kainz, Bernhard Karargyris, Alexandros Karthikesalingam, Alan Kenngott, Hannes Kleesiek, Jens Kofler, Florian Kooi, Thijs Kopp-Schneider, Annette Kozubek, Michal Kreshuk, Anna Kurc, Tahsin Landman, Bennett A. Litjens, Geert Madani, Amin Maier-Hein, Klaus Martel, Anne L. Mattson, Peter Meijering, Erik Menze, Bjoern Moons, Karel G.M. Müller, Henning Nichyporuk, Brennan Nickel, Felix Petersen, Jens Rafelski, Susanne M. Rajpoot, Nasir Reyes, Mauricio Riegler, Michael A. Rieke, Nicola Saez-Rodriguez, Julio Sánchez, Clara I. Shetty, Shravya Summers, Ronald M. Taha, Abdel A. Tiulpin, Aleksei Tsaftaris, Sotirios A. van Calster, Ben Varoquaux, Gaël Yaniv, Ziv R. Jäger, Paul F. Maier-Hein, Lena Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Heidelberg Division of Intelligent Medical Systems Germany NCT Heidelberg A Partnership Between DKFZ University Medical Center Heidelberg Germany Heidelberg Division of Medical Image Computing Germany Heidelberg Division of Intelligent Medical Systems Germany MRC Unit for Lifelong Health and Ageing UCL Centre for Medical Image Computing Department of Computer Science University College London London United Kingdom School of Biomedical Engineering and Imaging Science King’s College London London United Kingdom Instituto de Cálculo CONICET – Universidad de Buenos Aires Buenos Aires Argentina Centre for Medical Image Computing University College London London United Kingdom McGill University Montreal Canada Division of Computational Pathology Dept of Pathology & Laboratory Medicine Indiana University School of Medicine IU Health Information and Translational Sciences Building Indianapolis United States University of Pennsylvania Richards Medical Research Laboratories FL7 PhiladelphiaPA United States Department of Digital Medical Technologies Holon Institute of Technology Holon Israel European Federation for Medical Informatics Le Mont-sur-Lausanne Switzerland Center for Processing Speech and Images Department of Electrical Engineering KU Leuven Leuven Belgium partner site Frankfurt/Mainz a partnership between DKFZ and UCT Frankfurt Marburg Germany Heidelberg Germany Goethe University Frankfurt Department of Medicine Germany Goethe University Frankfurt Department of Informatics Germany and Frankfurt Cancer Insititute Germany Department of Computer Science IT University of Copenhagen Copenhagen Denmark Leibniz-Institut für Analytische Wissenschaften – ISAS – e.V. Dortmund Germany Imaging Platform Broad Institute of MIT and Harvard CambridgeMA United States Centre for Statistics in Medicine University of Oxford Oxford United Kingdom Center for Biomedical In

Validation metrics are key for tracking scientific progress and bridging the current chasm between artificial intelligence (AI) research and its translation into practice. However, increasing evidence shows that particularly in image analysis, metrics are often chosen inadequately. While taking into account the individual strengths, weaknesses, and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multi-stage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides the first reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. While focused on biomedical image analysis, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. The work serves to enhance global comprehension of a key topic in image analysis validation. © 2023, CC BY.

关键词： computer vision