Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Fernanda B. Viégas"'
Autor:
Martin Wattenberg, James Wexler, Dilip Krishnan, Doug Fritz, Fernanda B. Viégas, Jimbo Wilson, Kanit Wongsuphasawat, Dandelion Mane, Daniel Smilkov
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics. 24:1-12
We present a design study of the TensorFlow Graph Visualizer, part of the TensorFlow machine intelligence platform. This tool helps users understand complex machine learning architectures by visualizing their underlying dataflow graphs. The tool work
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87a216727cd70ee02bb3569caa2e0be8
https://doi.org/10.1109/tvcg.2017.2744878
https://doi.org/10.1109/tvcg.2017.2744878
Autor:
Greg S. Corrado, Mike Schuster, Fernanda B. Viégas, Zhifeng Chen, Melvin Johnson, Nikhil Thorat, Jeffrey Dean, Quoc V. Le, Macduff Hughes, Martin Wattenberg, Yonghui Wu, Maxim Krikun
Publikováno v:
Transactions of the Association for Computational Linguistics. 5:339-351
We propose a simple solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages. Our solution requires no changes to the model architecture from a standard NMT system but instead introduces an artificial to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5d1937b2d1cb257c81236e2bfac40c1
https://doi.org/10.1162/tacl_a_00065
https://doi.org/10.1162/tacl_a_00065
Publikováno v:
Geophysical Research Letters. 44:11-11,416
Aftershocks may be triggered by the stresses generated by preceding mainshocks. The temporal frequency and maximum size of aftershocks are well described by the empirical Omori and Bath laws, but spatial patterns are more difficult to forecast. Coulo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3729e544214a886fa05ba4e651140ceb
https://doi.org/10.1002/2017gl075875
https://doi.org/10.1002/2017gl075875
Publikováno v:
Nature. 560:632-634
Aftershocks are a response to changes in stress generated by large earthquakes and represent the most common observations of the triggering of earthquakes. The maximum magnitude of aftershocks and their temporal decay are well described by empirical
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4821217be1279fc3e75a11784a6d86aa
https://doi.org/10.1038/s41586-018-0438-y
https://doi.org/10.1038/s41586-018-0438-y
Publikováno v:
ICCV
Saliency methods can aid understanding of deep neural networks. Recent years have witnessed many improvements to saliency methods, as well as new ways for evaluating them. In this paper, we 1) present a novel region-based attribution method, XRAI, th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::504b14cca76f2a134039805da07d8c8f
https://doi.org/10.1109/iccv.2019.00505
https://doi.org/10.1109/iccv.2019.00505
Autor:
Jimbo Wilson, Fernanda B. Viégas, James Wexler, Martin Wattenberg, Mahima Pushkarna, Tolga Bolukbasi
Publikováno v:
IEEE transactions on visualization and computer graphics. 26(1)
A key challenge in developing and deploying Machine Learning (ML) systems is understanding their performance across a wide range of inputs. To address this challenge, we created the What-If Tool, an open-source application that allows practitioners t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7f5b9302104f9c46b7da3803fdce3640
https://pubmed.ncbi.nlm.nih.gov/31442996
https://pubmed.ncbi.nlm.nih.gov/31442996
Autor:
Fernanda B. Viégas, Narayan Hegde, Jason D. Hipp, Martin Wattenberg, Emily Reif, Been Kim, Greg S. Corrado, Michael Terry, Martin C. Stumpe, Daniel Smilkov, Carrie J. Cai
Publikováno v:
CHI
Machine learning (ML) is increasingly being used in image retrieval systems for medical decision making. One application of ML is to retrieve visually similar medical images from past patients (e.g. tissue from biopsies) to reference when making a me
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ae8a6a564e99a0b8ffe288668141b583
Publikováno v:
Seismological Research Letters. 88:126-130
Global Navigation Satellite System (GNSS) position time series are used pervasively in earthquake science to measure the surface response to earthquake cycle deformation. Characteristic usage cases are focused on the temporal windowing of position da
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0b4760ba57ecc339b76bd09bf1ebceda
https://doi.org/10.1785/0220160169
https://doi.org/10.1785/0220160169
Recent success in deep learning has generated immense interest among practitioners and students, inspiring many to learn about this new technology. While visual and interactive approaches have been successfully developed to help people more easily le
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8edc55906bef9c6d0a06d75f9b8822b5
http://arxiv.org/abs/1809.01587
http://arxiv.org/abs/1809.01587