检索结果-内蒙古大学图书馆

Deep Functional and Molecular Characterization of a High-Risk Undifferentiated Pleomorphic Sarcoma

Sarcoma 2020年第1期2020卷 6312480页

作者： Berlow, Noah E. Grasso, Catherine S. Quist, Michael J. Cheng, Mingshan Gandour-Edwards, Regina Hernandez, Brian S. Michalek, Joel E. Ryan, Christopher Spellman, Paul Pal, Ranadip Million, Lynn S. Renneker, Mark Keller, Charles Children's Cancer Therapy Development Institute Beaverton 97005 OR United States Electrical and Computer Engineering Texas Tech University Lubbock 79409 TX United States Division of Hematology-Oncology University of California Los Angeles 90095 CA United States Jackson Laboratory Bar Harbor 04609 ME United States Department of Pathology and Laboratory Medicine UC Davis Health System Sacramento 95817 CA United States Department of Epidemiology and Biostatistics University of Texas Health Science Center San Antonio San Antonio 78229 TX United States School of Medicine Oregon Health and Science University Portland 97239 OR United States Department of Radiation Oncology Stanford University Stanford 94305 CA United States Patient-Directed Consultations San Francisco 94116 CA United States Department of Family Medicine University of California San Francisco San Francisco 94143 CA United States

Nonrhabdomyosarcoma soft-tissue sarcomas (STSs) are a class of 50+ cancers arising in muscle and soft tissues of children, adolescents, and adults. Rarity of each subtype often precludes subtype-specific preclinical research, leaving many STS patients with limited treatment options should frontline therapy be insufficient. When clinical options are exhausted, personalized therapy assignment approaches may help direct patient care. Here, we report the results of an adult female STS patient with relapsed undifferentiated pleomorphic sarcoma (UPS) who self-drove exploration of a wide array of personalized Clinical Laboratory Improvement Amendments (CLIAs) level and research-level diagnostics, including state of the art genomic, proteomic, ex vivo live cell chemosensitivity testing, a patient-derived xenograft model, and immunoscoring. Her therapeutic choices were also diverse, including neoadjuvant chemotherapy, radiation therapy, and surgeries. Adjuvant and recurrence strategies included off-label and natural medicines, several immunotherapies, and N-of-1 approaches. Identified treatment options, especially those validated during the in vivo study, were not introduced into the course of clinical treatment but did provide plausible treatment regimens based on FDA-approved clinical agents. © 2020 Noah E. Berlow et al.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A simple neural attentive meta-learner

arXiv

引用

arXiv 2017年

作者： Mishra, Nikhil Rohaninejad, Mostafa Chen, Xi Abbeel, Pieter UC Berkeley Department of Electrical Engineering and Computer Science Embodied Intelligence

Deep neural networks excel in regimes with large amounts of data, but tend to struggle when data is scarce or when they need to adapt quickly to changes in the task. In response, recent work in meta-learning proposes training a meta-learner on a distribution of similar tasks, in the hopes of generalization to novel but related tasks by learning a high-level strategy that captures the essence of the problem it is asked to solve. However, many recent meta-learning approaches are extensively hand-designed, either using architectures specialized to a particular application, or hard-coding algorithmic components that constrain how the meta-learner solves the task. We propose a class of simple and generic meta-learner architectures that use a novel combination of temporal convolutions and soft attention;the former to aggregate information from past experience and the latter to pinpoint specific pieces of information. In the most extensive set of meta-learning experiments to date, we evaluate the resulting Simple Neural AttentIve Learner (or SNAIL) on several heavily-benchmarked tasks. On all tasks, in both supervised and reinforcement learning, SNAIL attains state-of-the-art performance by significant margins. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Correction: Variability of temperature measurements recorded by a wearable device by biological sex

引用

Biology of sex differences 2023年第1期14卷 82页

作者： Lauryn Keeler Bruce Patrick Kasl Severine Soltani Varun K Viswanath Wendy Hartogensis Stephan Dilchert Frederick M Hecht Anoushka Chowdhary Claudine Anglo Leena Pandya Subhasis Dasgupta Ilkay Altintas Amarnath Gupta Ashley E Mason Benjamin L Smarr Department of Biomedical Informatics UC San Diego Health University of California San Diego San Diego CA USA. Gene Lay Department of Bioengineering University of California San Diego 9500 Gilman Dr La Jolla San Diego CA USA. Bioinformatics and Systems Biology University of California San Diego San Diego CA USA. Department of Electrical and Computer Engineering University of California San Diego La Jolla CA USA. Osher Center for Integrative Health University of California San Francisco San Francisco CA USA. Department of Management Zicklin School of Business Baruch College The City University of New York New York NY USA. San Diego Supercomputer Center University of California San Diego San Diego CA USA. Halıcıoğlu Data Science Institute University of California San Diego San Diego CA USA. Gene Lay Department of Bioengineering University of California San Diego 9500 Gilman Dr La Jolla San Diego CA USA. bsmarr@eng.ucsd.edu. Halıcıoğlu Data Science Institute University of California San Diego San Diego CA USA. bsmarr@eng.ucsd.edu.

来源：评论

学校读者我要写书评

暂无评论

LEARNING VISUAL SERVOING WITH DEEP FEATURES AND FITTED Q-ITERATION

arXiv

引用

arXiv 2017年

作者： Lee, Alex X. Levine, Sergey Abbeel, Pieter UC Berkeley Department of Electrical Engineering and Computer Sciences OpenAI International Computer Science Institute

Visual servoing involves choosing actions that move a robot in response to observations from a camera, in order to reach a goal configuration in the world. Standard visual servoing approaches typically rely on manually designed features and analytical dynamics models, which limits their generalization capability and often requires extensive application-specific feature and model engineering. In this work, we study how learned visual features, learned predictive dynamics models, and reinforcement learning can be combined to learn visual servoing mechanisms. We focus on target following, with the goal of designing algorithms that can learn a visual servo using low amounts of data of the target in question, to enable quick adaptation to new targets. Our approach is based on servoing the camera in the space of learned visual features, rather than image pixels or manually-designed keypoints. We demonstrate that standard deep features, in our case taken from a model trained for object classification, can be used together with a bilinear predictive model to learn an effective visual servo that is robust to visual variation, changes in viewing angle and appearance, and occlusions. A key component of our approach is to use a sample-efficient fitted Q-iteration algorithm to learn which features are best suited for the task at hand. We show that we can learn an effective visual servo on a complex synthetic car following benchmark using just 20 training trajectory samples for reinforcement learning. We demonstrate substantial improvement over a conventional approach based on image pixels or hand-designed keypoints, and we show an improvement in sample-efficiency of more than two orders of magnitude over standard model-free deep reinforcement learning algorithms. Videos are available at http://***/visual_servoing. Copyright © 2017, The Authors. All rights reserved.

关键词： Visual servoing

来源：评论

学校读者我要写书评

暂无评论

Binarized Convolutional Neural Networks with Separable Filters for Efficient Hardware Acceleration

arXiv

引用

arXiv 2017年

作者： Lin, Jeng-Hau Xing, Tianwei Zhao, Ritchie Zhang, Zhiru Srivastava, Mani Tu, Zhuowen Gupta, Rajesh K. Department of Computer Science and Engineering UC San Diego United States Department of Electrical Engineering UC Los Angeles United States Department of Electrical and Computer Engineering Cornell University Department of Cognitive Science UC San Diego United States

State-of-the-art convolutional neural networks are enormously costly in both compute and memory, demanding massively parallel GPUS for execution. Such networks strain the computational capabilities and energy available to embedded and mobile processing platforms, restricting their use in many important applications. In this paper, we push the boundaries of hardware-effective CNN design by proposing BCNN with Separable Filters (BCNNw/SF), which applies Singular Value Decomposition (SVD) on BCNN kernels to further reduce computational and storage complexity. To enable its implementation, we provide a closed form of the gradient over SVD to calculate the exact gradient with respect to every binarized weight in backward propagation. We verify BCNNw/SF on the MNIST, CIFAR-10, and SVHN datasets, and implement an accelerator for CIFAR-10 on FPGA hardware. Our BCNNw/SF accelerator realizes memory savings of 17% and execution time reduction of 31:3% compared to BCNN with only minor accuracy sacrifices. Copyright © 2017, The Authors. All rights reserved.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Combinatorial Prophet Inequalities 17

Combinatorial Prophet Inequalities

引用

Annual ACM-Society for Industrial and Applied Mathmatics Symposium on Discrete Algorithms

作者： Aviad Rubinstein Sahil Singla Electrical Engineering and Computer Sciences UC Berkeley Computer Science Department Carnegie Mellon University

ISBN: (纸本)9781510836358

We introduce a novel framework of Prophet Inequalities for combinatorial valuation functions. For a (non-monotone) submodular objective function over an arbitrary matroid feasibility constraint, we give an O(1)-competitive algorithm. For a monotone subadditive objective function over an arbitrary downward-closed feasibility constraint, we give an O(log n log~2 r)-competitive algorithm (where r is the cardinality of the largest feasible subset). Inspired by the proof of our subadditive prophet inequality, we also obtain an O(log n·log~2 r)-competitive algorithm for the Secretary Problem with a monotone subadditive objective function subject to an arbitrary downward-closed feasibility constraint. Even for the special case of a cardinality feasibility constraint, our algorithm circumvents an Ω({the square root of}n) lower bound by Bateni, Hajiaghayi, and Zadimoghaddam [10] in a restricted query model. En route to our submodular prophet inequality, we prove a technical result of independent interest: we show a variant of the Correlation Gap Lemma [14, 1] for non-monotone submodular functions.

关键词： subadditive inequalities base number algorithms Objective function Arbitrary Proof Monotone

来源：评论

学校读者我要写书评

暂无评论

High Dimensional Data Enrichment: Interpretable, Fast, and Data-Efficient

arXiv

引用

arXiv 2018年

作者： Asiaee, Amir Oymak, Samet Coombes, Kevin R. Banerjee, Arindam Mathematical Biosciences Institute The Ohio State University ColumbusOH43210 United States Department of Electrical and Computer Engineering UC Riverside RiversideCA92507 United States Departments of Biomedical Informatics The Ohio State University ColumbusOH43210 United States Department of Computer Science and Engineering University of Minnesota MinneapolisMN55455 United States

We consider the problem of multi-task learning in the high dimensional setting. In particular, we introduce an estimator and investigate its statistical and computational properties for the problem of multiple connected linear regressions known as Data Sharing. The between-tasks connections are captured by a cross-tasks common parameter, which gets refined by per-task individual parameters. Any convex function, e.g., norm, can characterize the structure of both common and individual parameters. We delineate the sample complexity of our estimator and provide high probability non-asymptotic bound for estimation error of all parameters under a geometric condition. We show that the recovery of the common parameter benefits from all of the pooled samples. We propose an iterative estimation algorithm with a geometric convergence rate and supplement our theoretical analysis with experiments on synthetic data. Overall, we present a first through statistical and computational analysis of inference in the data sharing model. Copyright © 2018, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Approximation Algorithms for Label Cover and The Log-Density Threshold 17

Approximation Algorithms for Label Cover and The Log-Density...

引用

Annual ACM-Society for Industrial and Applied Mathmatics Symposium on Discrete Algorithms

作者： Eden Chlamtac Pasin Manurangsi Dana Moshkovitz Aravindan Vijayaraghavan Department of Computer Science Ben-Gurion University Department of Electrical Engineering and Computer Science UC Berkeley Department of Computer Science UT Austin Department of Electrical Engineering and Computer Science Northwestern University

ISBN: (纸本)9781510836358

Many known optimal NP-hardness of approximation results are reductions from a problem called LABEL-COVER. The input is a bipartite graph G = (L, R, E) and each edge e = (x, y) ∈ E carries a projection π_e that maps labels to x to labels to y. The objective is to find a labeling of the vertices that satisfies as many of the projections as possible. It is believed that the best approximation ratio efficiently achievable for LABEL-COVER is of the form N~(-c) where N = nk, n is the number of vertices, k is the number of labels, and 0 < c < 1 is some constant. Inspired by a framework originally developed for DENSEST k-SUBGRAPH, we propose a "log density threshold" for the approximability of Label-Cover. Specifically, we suggest the possibility that the Label-Cover approximation problem undergoes a computational phase transition at the same threshold at which local algorithms for its random counterpart fail. This threshold is N~(3-2{sqroot})≈N~(-0.17). We then design, for any ε > 0, a polynomial-time approximation algorithm for semi-random LABEL-COVER whose approximation ratio is N~(3-2{sqroot}+ε). In our semi-random model, the input graph is random (or even just expanding), and the projections on the edges are arbitrary. For worst-case LABEL-COVER we show a polynomial-time algorithm whose approximation ratio is roughly N~(-0.233). The previous best efficient approximation ratio was N~(-0.25). We present some evidence towards an N~(-c) threshold by constructing integrality gaps for N~(Ω(1)) rounds of the Sum-of-squares/Lasserre hierarchy of the natural relaxation of Label Cover. For general 2CSP the "log density threshold" is N~(-0.25), and we give a polynomial-time algorithm in the semi-random model whose approximation ratio is N~(-0.25+ε) for any ε>0.

关键词： Approximation algorithms approximation vertex head

来源：评论

学校读者我要写书评

暂无评论

Mining urban lifestyles: urban computing, human behavior and recommender systems

arXiv

引用

arXiv 2019年

作者： Xu, Sharon Clemente, Riccardo Di González, Marta C. Department of Civil and Environmental Engineering Massachusetts Institute of Technology CambridgeMA02139 United States Centre for Advanced Spatial Analysis University College London LondonWC1E 6BT United Kingdom Department of Computer Science University of Exeter ExeterEX4 4PY United Kingdom Department of City and Regional Planning UC Berkeley 406 Wurster Hall Berkeley94720 United States Lawrence Berkeley National Laboratory Cyclotron Road Berkeley94720 United States

This is a postprint of the 5th chapter published in the book Big Data Recommender Systems - Volume 2: Application Paradigms and is subject to Institution of engineering and Technology Copyright. The copy of record is ... 详细信息

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Erratum: Towards a muon collider

引用

The European Physical Journal C 2024年第1期84卷 1-4页

作者： Accettura, Carlotta Adams, Dean Agarwal, Rohit Ahdida, Claudia Aimè, Chiara Amapane, Nicola Amorim, David Andreetto, Paolo Anulli, Fabio Appleby, Robert Apresyan, Artur Apyan, Aram Arsenyev, Sergey Asadi, Pouya Mahmoud, Mohammed Attia Azatov, Aleksandr Back, John Balconi, Lorenzo Bandiera, Laura Barlow, Roger Bartosik, Nazar Barzi, Emanuela Batsch, Fabian Bauce, Matteo Berg, J. Scott Bersani, Andrea Bertarelli, Alessandro Bertolin, Alessandro Black, Kevin Boattini, Fulvio Bogacz, Alex Bonesini, Maurizio Bordini, Bernardo Bottaro, Salvatore Bottura, Luca Braghieri, Alessandro Breschi, Marco Bruhwiler, Natalie Buffat, Xavier Buonincontri, Laura Burrows, Philip N. Burt, Graeme Buttazzo, Dario Caiffi, Barbara Calviani, Marco Calzaferri, Simone Calzolari, Daniele Capdevilla, Rodolfo Carli, Christian Casaburo, Fausto Casarsa, Massimo Castelli, Luca Catanesi, Maria Gabriella Cavallucci, Lorenzo Cavoto, Gianluca Celiberto, Francesco Giovanni Celona, Luigi Cerri, Alessandro Cesarini, Gianmario Cesarotti, Cari Chachamis, Grigorios Chance, Antoine Chen, Siyu Chien, Yang-Ting Chiesa, Mauro Colaleo, Anna Collamati, Francesco Collazuol, Gianmaria Costa, Marco Craig, Nathaniel Curatolo, Camilla Curtin, David Da Molin, Giacomo Dam, Magnus Damerau, Heiko Dasu, Sridhara de Blas, Jorge De Curtis, Stefania De Matteis, Ernesto De Rosa, Stefania Delahaye, Jean-Pierre Denisov, Dmitri Denizli, Haluk Densham, Christopher Dermisek, Radovan Di Luzio, Luca Di Meco, Elisa Di Micco, Biagio Dienes, Keith Diociaiuti, Eleonora Dorigo, Tommaso Dudarev, Alexey Edgecock, Robert Errico, Filippo Fabbrichesi, Marco Farinon, Stefania Ferrari, Anna Somoza, Jose Antonio Ferreira Filthaut, Frank Fiorina, Davide Fol, Elena Forslund, Matthew Franceschini, Roberto Ximenes, Rui Franqueira Gabrielli, Emidio Gallinaro, Michele Garosi, Francesco Giambastiani, Luca Gianelle, Alessio Gilardoni, Simone Giove, Dario Augusto Giraldin, Carlo Glioti, Alfredo Greco, Mario Greljo, Admir Groeber, Ramona Grojean, Christophe Grudiev, Alexej Gu, Jiayin Han, Chengcheng Han, T Organisation Européenne pour la Recherche Nucléaire (CERN) Geneva Switzerland STFC Rutherford Appleton Laboratory (RAL) Oxford UK Computer Science Department University of California (UC) Berkeley USA Dipartimento di Fisica Università di Pavia Pavia Italy INFN Sezione di Pavia Pavia Italy INFN Sezione di Torino Turin Italy Dipartimento di Fisica Università di Torino Turin Italy INFN Sezione di Padova Padua Italy INFN Sezione di Roma Rome Italy School of Physics and Astronomy University of Manchester Manchester UK Fermi National Accelerator Laboratory Batavia USA Department of Physics Brandeis University Waltham USA IRFU CEA University Paris-Saclay Gif-sur-Yvette France Center for Theoretical Physics Massachusetts Institute of Technology Cambridge USA Center for High Energy Physics (CHEP-FU) Fayoum University El-Fayoum Egypt SISSA International School for Advanced Studies Trieste Italy INFN Sezione di Trieste Trieste Italy Department of Physics University of Warwick Coventry UK Dipartimento di Fisica Università di Milano Milan Italy INFN Laboratori Acceleratori e Superconduttività Applicata (LASA) Milan Italy INFN Sezione di Ferrara Ferrara Italy School of Computing and Engineering The University of Huddersfield Huddersfield UK Ohio State University Columbus USA Brookhaven National Laboratory Upton USA INFN Sezione di Genova Genoa Italy University of Wisconsin Wisconsin USA Center for Advanced Studies of Accelerators Jefferson Lab Newport News USA INFN Sezione di Milano Bicocca Milan Italy Dipartimento di Fisica Università di Milano Bicocca Milan Italy Scuola Normale Superiore Pisa Italy INFN Sezione di Pisa Pisa Italy Dipartimento di Ingegneria dell’Energia Elettrica e dell’Informazione Università di Bologna Bologna Italy INFN Sezione di Bologna Bologna Italy Department of Physics University of California (UC) Berkeley USA Dipartimento di Fisica e Astronomia Università di Padova Padoa Italy John Adams Institute University of O

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：