Filters








7 Hits in 9.0 sec

A Survey of Deep Active Learning [article]

Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-Yao Huang, Zhihui Li, Brij B. Gupta, Xiaojiang Chen, Xin Wang
2021 arXiv   pre-print
This is mainly because before the rise of DL, traditional machine learning requires relatively few labeled samples. Therefore, early AL is difficult to reflect the value it deserves.  ...  Active learning (AL) attempts to maximize the performance gain of the model by marking the fewest samples.  ...  In Machine Learning, Proceedings of the Twenty-Third International Conference (ICML 2006), Pittsburgh, Pennsylvania, USA, June 25-29, 2006 (ACM International Conference Proceeding Series, Vol. 148  ... 
arXiv:2009.00236v2 fatcat:zuk2doushzhlfaufcyhoktxj7e

Accelerating Safe Reinforcement Learning with Constraint-mismatched Policies [article]

Tsung-Yen Yang and Justinian Rosca and Karthik Narasimhan and Peter J. Ramadge
2021 arXiv   pre-print
We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy.  ...  In our experiments on five different control tasks, our algorithm consistently outperforms several state-of-the-art baselines, achieving 10 times fewer constraint violations and 40% higher reward on average  ...  Acknowledgements The authors would like to thank members of the Princeton NLP Group, the anonymous reviewers, and the area chair for their comments.  ... 
arXiv:2006.11645v3 fatcat:ngboxu47t5fm3gojgnym6yqala

Road Intersection Detection through Finding Common Sub-Tracks between Pairwise GNSS Traces

Xingzhe Xie, Wilfried Philips
2017 ISPRS International Journal of Geo-Information  
In Proceedings of the Seventeenth International Conference on Machine Learning (ICML ’00), Stanford, CA, USA, 29 June2 July 2000; pp. 727–734. 18.  ...  In Proceedings of the 20th International Conference on Advances in Geographic Information Systems, Redondo Beach, CA, USA, 7–9 November 2012; pp. 89–98. 8.  ... 
doi:10.3390/ijgi6100311 fatcat:tlcfdxwpmrhuviyaighn4ljdnq

The statistical advantage of automatic NLG metrics at the system level

Johnny Wei, Robin Jia
2021 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)   unpublished
Our analysis compares the adjusted error of metrics to humans and a derived, perfect segment-level annotator, both of which are unbiased estimators dependent on the number of judgments collected.  ...  Measuring this error is complicated: predictions are evaluated against noisy, human predicted labels instead of the ground truth, and metric predictions fluctuate based on the test sets they were calculated  ...  Alex Fabbri provided a scored version of the SummEval dataset. We thank all who have made our work possible.  ... 
doi:10.18653/v1/2021.acl-long.533 fatcat:dun7eo4lcraqngb6eli53tpmb4

Extracting perceived landscape properties from text sources

Olga Koblet
2020
in the concept of tranquillity concentrating on the Lake District region.  ...  Using this workflow we were able to collect almost 7000 rich first-person narratives of the Lake District, comprising ca. 8 million of words.  ...  RSP gratefully acknowledges support from the Swiss National Science Foundation Project EVA (200021E-166788) and the University Research Priority Programme on Language and Space.  ... 
doi:10.5167/uzh-193201 fatcat:nojlrh7vlnfybnvv5sx6lpzkfq

Primary Encoder: Laura Weakly Designer: Karin Dalziel Encoders and Proofreaders: International Program Committee Local Organizing Committee Conference Volunteers Welcome to Digital Humanities 2013

Matt Bosley, Matthew Lavin, Elizabeth Lorang, Keith Nickum, Erin Pedigo, Hannah Vahle, Bethany Nowviskie, Craig Bellamy, John Bradley, Paul Caton, Carolyn Guertin, Ian Johnson (+61 others)
2013 unpublished
Welcome to the University of Nebraska-Lincoln and to Digital Humanities 2013. The theme we have chosen for this year's conference is "Freedom to Explore."  ...  We hope you can come to our open house during the conference and meet some of our faculty and graduate students.  ...  International Program Committee Acknowledgements The University of Queensland is proud to be in partnership with the National eResearch Collaboration Tools and Resources (NeCTAR) project to create a  ... 
fatcat:bibtuxjcgzdtpgda6kjat2m5hu

Qualitätstransparenz in Deutschland und deren Anwendung zur Steigerung der Behandlungsqualität im Krankenhaus [article]

Christoph Pross, Technische Universität Berlin, Technische Universität Berlin, Reinhard Busse
2017
Yet, the scientific knowledge around quality of care transparency and its effects on outcomes is fragmented, outdated and, in the German context, rudimentary.  ...  Second, this project uses regression analysis and stochastic efficiency modeling to examine the influence of certain structural factors on quality and efficiency in hospital service delivery.  ...  Tom Rice, professor at the Department for Health Policy and Management at the University of California, Los Angeles for helpful comments on earlier versions of this article and his support in getting Hospital  ... 
doi:10.14279/depositonce-6139 fatcat:zjt4dqrjjjbfbmf4ww74yxl25u