检索结果-内蒙古大学图书馆

Common Limitations of Image Processing Metrics: A Picture Story

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Reinke, Annika Tizabi, Minu D. Sudre, Carole H. Eisenmann, Matthias Rädsch, Tim Baumgartner, Michael Acion, Laura Antonelli, Michela Arbel, Tal Bakas, Spyridon Bankhead, Peter Benis, Arriel Blaschko, Matthew Buettner, Florian Cardoso, M. Jorge Chen, Jianxu Cheplygina, Veronika Christodoulou, Evangelia Cimini, Beth A. Collins, Gary S. Engelhardt, Sandy Farahani, Keyvan Ferrer, Luciana Galdran, Adrian van Ginneken, Bram Glocker, Ben Godau, Patrick Haase, Robert Hamprecht, Fred Hashimoto, Daniel A. Heckmann-Nötzel, Doreen Hirsch, Peter Hoffman, Michael M. Huisman, Merel Isensee, Fabian Jannin, Pierre Kahn, Charles E. Kainmueller, Dagmar Kainz, Bernhard Karargyris, Alexandros Karthikesalingam, Alan Kavur, A. Emre Kenngott, Hannes Kleesiek, Jens Kleppe, Andreas Koehler, Sven Kofler, Florian Kopp-Schneider, Annette Kooi, Thijs 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 Moher, David Moons, Karel G.M. Müller, Henning Nichyporuk, Brennan Nickel, Felix Noyan, M. Alican Petersen, Jens Polat, Gorkem Rafelski, Susanne M. Rajpoot, Nasir Reyes, Mauricio Rieke, Nicola Riegler, Michael A. Rivaz, Hassan Saez-Rodriguez, Julio Sánchez, Clara I. Schroeter, Julien Saha, Anindo Selver, M. Alper Sharan, Lalith Shetty, Shravya Smeden, Maarten V.A.N. Stieltjes, Bram Summers, Ronald M. Taha, Abdel A. Tiulpin, Aleksei Tsaftaris, Sotirios A. Calster, Ben V.A.N. Varoquaux, Gaël Wiesenfarth, Manuel Yaniv, Ziv R. Jäger, Paul Maier-Hein, Lena Division of Intelligent Medical Systems and HI Helmholtz Imaging Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Division of Intelligent Medical Systems Heidelberg Germany NCT Heidelberg DKFZ University Medical Center Heidelberg 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 Division of Medical Image Computing Heidelberg Germany Instituto de Cálculo CONICET – Universidad de Buenos Aires Buenos Aires Argentina Centre for Medical Image Computing University College London London United Kingdom McGill University Montréal 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 Institute of Genetics and Cancer University of Edinburgh Edinburgh United Kingdom 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 Kasteelpark Arenberg 10 - box 2441 Leuven3001 Belgium Frankfurt/Mainz DKFZ UCT Frankfurt-Marburg Germany Heidelberg Germany Goethe University Frankfurt Department of Medicine Germany Goethe University Frankfurt Department of Informatics Germany Frankfurt Cancer Insititute Germany Leibniz-Institut für Analytische Wissenschaften – ISAS – e.V. Dortmund Germany Department of Computer Science IT University of Copenhagen Copenhagen Denmark Imaging Platform Broad Institute of MIT and Harvard CambridgeMA United States Centre for St

While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation. Performance metrics are particularly key for meaningful, objective, and transparent performance assessment and validation of the used automatic algorithms, but relatively little attention has been given to the practical pitfalls when using specific metrics for a given image analysis task. These are typically related to (1) the disregard of inherent metric properties, such as the behaviour in the presence of class imbalance or small target structures, (2) the disregard of inherent data set properties, such as the non-independence of the test cases, and (3) the disregard of the actual biomedical domain interest that the metrics should reflect. This living dynamically document has the purpose to illustrate important limitations of performance metrics commonly applied in the field of image analysis. In this context, it focuses on biomedical image analysis problems that can be phrased as image-level classification, semantic segmentation, instance segmentation, or object detection task. The current version is based on a Delphi process on metrics conducted by an international consortium of image analysis experts from more than 60 institutions worldwide. © 2021, CC BY.

关键词： Medical imaging

Toward Abstraction from Multi-modal Data: Empirical Studies on Multiple Time-scale Recurrent Models

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Zhong, Junpei Cangelosi, Angelo Ogata, Tetsuya Aomi 2-3-26 Tokyo Japan Centre for Robotics and Neural Systems Plymouth University Plymouth United Kingdom Lab for Intelligent Dynamics and Representation Waseda University Tokyo Japan

The abstraction tasks are challenging for multi-modal sequences as they require a deeper semantic understanding and a novel text generation for the data. Although the recurrent neural networks (RNN) can be used to model the context of the time-sequences, in most cases the long-term dependencies of multi-modal data make the back-propagation through time training of RNN tend to vanish in the time domain. Recently, inspired from Multiple Time-scale Recurrent Neural Network (MTRNN) [1], an extension of Gated Recurrent Unit (GRU), called Multiple Time-scale Gated Recurrent Unit (MTGRU), has been proposed [2] to learn the long-term dependencies in natural language processing. Particularly it is also able to accomplish the abstraction task for paragraphs given that the time constants are well defined. In this paper, we compare the MTRNN and MTGRU in terms of its learning performances as well as their abstraction representation on higher level (with a slower neural activation). This was done by conducting two studies based on a smaller data-set (two-dimension time sequences from non-linear functions) and a relatively large data-set (43-dimension time sequences from iCub manipulation tasks with multi-modal data). We conclude that gated recurrent mechanisms may be necessary for learning long-term dependencies in large dimension multi-modal data-sets (e.g. learning of robot manipulation), even when natural language commands was not involved. But for smaller learning tasks with simple time-sequences, generic version of recurrent models, such as MTRNN, were sufficient to accomplish the abstraction task. Copyright © 2017, The Authors. All rights reserved.

关键词： Semantics

Hydrogels: Near‐Infrared Light‐Sensitive Polyvinyl Alcohol Hydrogel Photoresist for Spatiotemporal Control of Cell‐Instructive 3D Microenvironments (Adv. Mater. 10/2018)

学校读者我要写书评

暂无评论

Advanced Materials 2018年第10期30卷

作者： Xiao‐Hua Qin Xiaopu Wang Markus Rottmar Bradley J. Nelson Katharina Maniura‐Weber Laboratory for Biointerfaces Empa‐Swiss Federal Laboratories for Materials Science and Technology CH‐9014 St. Gallen Switzerland Multi‐Scale Robotics Lab Institute of Robotics and Intelligent Systems ETH Zürich CH‐8092 Zürich Switzerland

A complete automated chain for flexible assembly using recognition, planning and sensor-based execution 47

学校读者我要写书评

暂无评论

A complete automated chain for flexible assembly using recog...

47th International Symposium on robotics, ISR 2016

作者： Nottensteiner, Korbinian Bodenmüller, Tim Kassecker, Michael Roa, Máximo A. Stemmer, Andreas Stouraitis, Theodoros Seidel, Daniel Thomas, Ulrike Germany Sensor Based Robotic Systems and Intelligent Assistance Systems TU Munich Germany Robotics and Human Machine Interaction Lab TU Chemnitz Germany

ISBN: (纸本)9783800742318

This paper presents a fully automated system for automatic assembly of aluminum profile constructions. This high grade of automation of the entire process chain requires novel strategies in recognition, planning and execution. The system includes an assembly sequence planner integrated with a grasp planning tool, a knowledge-based reasoning method, a skill-based code generation, and an error tolerant execution engine. The modular structure of the system allows its adaptation to new products, which can prove especially useful for SMEs producing small lot sizes. The system is robust and stable, as demonstrated with the repeated execution of different geometric assemblies. © 2016 VDE VERLAG GMBH Berlin Offenbach.

关键词： Knowledge based systems

A New Data Source for Inverse Dynamics Learning

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Kappler, Daniel Meier, Franziska Ratliff, Nathan Schaal, Stefan AMD MPI for Intelligent Systems Tubingen Germany Lula Robotics Inc Seattle United States CLMC Lab University of Southern California Los Angeles United States RSE Lab University of Washington Seattle United States

Modern robotics is gravitating toward increasingly collaborative human robot interaction. Tools such as acceleration policies can naturally support the realization of reactive, adaptive, and compliant robots. These tools require us to model the system dynamics accurately-a difficult task. The fundamental problem remains that simulation and reality diverge-we do not know how to accurately change a robot's state. Thus, recent research on improving inverse dynamics models has been focused on making use of machine learning techniques. Traditional learning techniques train on the actual realized accelerations, instead of the policy's desired accelerations, which is an indirect data source. Here we show how an additional training signal-measured at the desired accelerations-can be derived from a feedback control signal. This effectively creates a second data source for learning inverse dynamics models. Furthermore, we show how both the traditional and this new data source, can be used to train task-specific models of the inverse dynamics, when used independently or combined. We analyze the use of both data sources in simulation and demonstrate its effectiveness on a real-world robotic platform. We show that our system incrementally improves the learned inverse dynamics model, and when using both data sources combined converges more consistently and faster. Copyright © 2017, The Authors. All rights reserved.

关键词： Human robot interaction

Metal–Organic Frameworks: In-Flow MOF Lithography (Adv. Mater. Technol. 6/2019)

学校读者我要写书评

暂无评论

Advanced Materials Technologies 2019年第6期4卷

作者： Semih Sevim Carlos Franco Hongjun Liu Hervé Roussel Laetitia Rapenne Juan Rubio-Zuazo Xiang-Zhong Chen Salvador Pané David Muñoz-Rojas Andrew J. deMello Josep Puigmartí-Luis Institute of Chemical and Bioengineering ETH Zurich Vladimir Prelog Weg 1 8093 Zurich Switzerland Institute of Engineering Univ. Grenoble Alpes CNRS Grenoble INP LMGP F-38000 Grenoble France Spanish CRG BM25-SpLine Beamline at the ESRF 71 Av des Martyrs CS 40220 38043 Grenoble Cedex 9 France Instituto de Ciencia de Materiales de Madrid—ICMM/CSIC Cantoblanco E-28049 Madrid Spain Multi-Scale Robotics Lab (MSRL) Institute of Robotics and Intelligent Systems (IRIS) ETH Zurich Tannenstrasse 3 8092 Zurich Switzerland

Numerical search for local (partial) differential flatness

学校读者我要写书评

暂无评论

Numerical search for local (partial) differential flatness

IEEE/RSJ International Conference on intelligent Robots and systems

作者： Carmelo Sferrazza Diego Pardo Jonas Buchli Agile Dexterous Robotics Lab at the Institute of Robotics and Intelligent Systems ETH Zurich Switzerland

ISBN: (纸本)9781509037636

Differential flatness is a property of certain systems that greatly simplifies the generation of optimal and dynamically feasible trajectories. Using a differentially flat model, there is no need to integrate the system dynamics to retrieve the states and the constraints of the optimization problem are simpler. Recently, the concept of partial differential flatness has been introduced covering a broader class of systems. In particular, it allows to reduce the need for integration by limiting it to a subset of the states. However, finding an analytical expression for the (partial) differential flatness requires the manipulation of the equations of motion in a very specific manner such that a series of properties are fulfilled. In general, finding such analytical model is not straightforward nor compatible with algorithmic models. In order to tackle this problem, in this paper we present a numerical method to find a (partially) differentially flat model of a system around a collection of states and inputs trajectories. We present results on three underactuated nonlinear systems (cart-pole, planar ballbot and a 3D quadrotor). As use case examples, we show online trajectory re-planning tasks. The validity of the trajectories obtained with the locally flat models is verified by forward integrating the original equations of motion together with an optimal stabilizer.

关键词： Trajectory Mathematical model Numerical models Robots Optimization Analytical models System dynamics

Hybrid control trajectory optimization under uncertainty

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Pajarinen, Joni Kyrki, Ville Koval, Michael Srinivasa, Siddhartha Peters, Jan Neumann, Gerhard labs TU Darmstadt Germany Department of Electrical Engineering and Automation Aalto University Finland Robotics Institute Carnegie Mellon University United States IAS lab TU Darmstadt Germany Max Planck Institute for Intelligent Systems Tuebingen Germany Lincoln Centre for Autonomous Systems University of Lincoln United Kingdom

— Trajectory optimization is a fundamental problem in robotics. While optimization of continuous control trajectories is well developed, many applications require both discrete and continuous, i.e. hybrid controls. Finding an optimal sequence of hybrid controls is challenging due to the exponential explosion of discrete control combinations. Our method, based on Differential Dynamic Programming (DDP), circumvents this problem by incorporating discrete actions inside DDP: we first optimize continuous mixtures of discrete actions, and, subsequently force the mixtures into fully discrete actions. Moreover, we show how our approach can be extended to partially observable Markov decision processes (POMDPs) for trajectory planning under uncertainty. We validate the approach in a car driving problem where the robot has to switch discrete gears and in a box pushing application where the robot can switch the side of the box to push. The pose and the friction parameters of the pushed box are initially unknown and only indirectly observable. Copyright © 2017, The Authors. All rights reserved.

关键词： Aerodynamics

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Srivastava, Aarohi Rastogi, Abhinav Rao, Abhishek Shoeb, Abu Awal Md Abid, Abubakar Fisch, Adam Brown, Adam R. Santoro, Adam Gupta, Aditya Garriga-Alonso, Adrià Kluska, Agnieszka Lewkowycz, Aitor Agarwal, Akshat Power, Alethea Ray, Alex Warstadt, Alex Kocurek, Alexander W. Safaya, Ali Tazarv, Ali Xiang, Alice Parrish, Alicia Nie, Allen Hussain, Aman Askell, Amanda Dsouza, Amanda Slone, Ambrose Rahane, Ameet Iyer, Anantharaman S. Andreassen, Anders Madotto, Andrea Santilli, Andrea Stuhlmüller, Andreas Dai, Andrew La, Andrew Lampinen, Andrew Zou, Andy Jiang, Angela Chen, Angelica Vuong, Anh Gupta, Animesh Gottardi, Anna Norelli, Antonio Venkatesh, Anu Gholamidavoodi, Arash Tabassum, Arfa Menezes, Arul Kirubarajan, Arun Mullokandov, Asher Sabharwal, Ashish Herrick, Austin Efrat, Avia Erdem, Aykut Karakaş, Ayla Ryan Roberts, B. Loe, Bao Sheng Zoph, Barret Bojanowski, Bartlomiej Özyurt, Batuhan Hedayatnia, Behnam Neyshabur, Behnam Inden, Benjamin Stein, Benno Ekmekci, Berk Lin, Bill Yuchen Howald, Blake Orinion, Bryan Diao, Cameron Dour, Cameron Stinson, Catherine Argueta, Cedrick Ramírez, César Ferri Singh, Chandan Rathkopf, Charles Meng, Chenlin Baral, Chitta Wu, Chiyu Callison-Burch, Chris Waites, Chris Voigt, Christian Manning, Christopher D. Potts, Christopher Ramirez, Cindy Rivera, Clara E. Siro, Clemencia Raffel, Colin Ashcraft, Courtney Garbacea, Cristina Sileo, Damien Garrette, Dan Hendrycks, Dan Kilman, Dan Roth, Dan Freeman, Daniel Khashabi, Daniel Levy, Daniel González, Daniel Moseguí Perszyk, Danielle Hernandez, Danny Chen, Danqi Ippolito, Daphne Gilboa, Dar Dohan, David Drakard, David University of Notre Dame United States Google United States Rutgers University United States Stanford University United States MIT United States DeepMind United Kingdom University of Cambridge United Kingdom University of Amsterdam Netherlands Google Research Blueshift Team NeuralSpace New York University United States Cornell University United States Koç University Turkey University of California Irvine United States Duke Kunshan University China Anthropic United States Georgia Tech United States KNC Neural Calculus National Public School - HSR Layout HKUST Hong Kong Sapienza University of Rome Italy Ought Google Research United States UC Berkeley United States Thapar University India Amazon United States Microsoft United States University of Pennsylvania United States Imperial College London United Kingdom Allen Instituite for AI Tel Aviv University Yale University United States Wroclaw University of Science and Technology Poland Blueshift Max Planck Institute for Mathematics in the Sciences Germany Bauhaus-Universität Weimar Germany Thomson Reuters Special Services University of Southern California United States Rice University United States Queen's University Kingston Canada Princeton University United States Universitat Politècnica de València Spain Juelich Research Center Germany Arizona State University United States Carnegie Mellon University United States Karlsruhe Institute of Technology Germany UNC Chapel Hill United States University of Michigan United States KU Leuven Belgium Harvard University United States ML Collective University of Virginia United States University of Edinburgh United Kingdom Research Institutes of Sweden Sweden University of Washington United States Facebook AI Research United States Mila Canada Landskape AI Umeå University Sweden Brain Team OpenAI Brown University United States MIT Media Lab United States Hacettepe University Turkey Saarland University Germany National University of Singapore Singapore Strathmore University

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG-bench). BIG-bench currently consists of 204 tasks, contributed by 450 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood development, math, common-sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models. We evaluate the behavior of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. In addition, a team of human expert raters performed all tasks in order to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with rater performance);performance is remarkably similar across model classes, though with benefits from sparsity;tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit "breakthrough" behavior at a critical scale often involve multiple steps or components, or brittle metrics;social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting. Copyright © 2022, The Authors. All rights reserved.

关键词： Software design