Zobrazeno 1 - 10
of 57
pro vyhledávání: '"Richard S. Zemel"'
Autor:
Jörn-Henrik Jacobsen, Matthias Bethge, Felix A. Wichmann, Claudio Michaelis, Wieland Brendel, Richard S. Zemel, Robert Geirhos
Publikováno v:
Nature Machine Intelligence. 2:665-673
Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today's machine intelligence. Numerous success stories have rapidly spread all over science, industry and society, but its limitations have only recently
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e33ec72d0d48ebc3211b96c85b75d6a9
https://doi.org/10.1038/s42256-020-00257-z
https://doi.org/10.1038/s42256-020-00257-z
Slang is a common type of informal language, but its flexible nature and paucity of data resources present challenges for existing natural language systems. We take an initial step toward machine generation of slang by developing a framework that mod
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::119ec51c4d64279950edd5b9a1aab488
Publikováno v:
FAT
How do we learn from biased data? Historical datasets often reflect historical prejudices; sensitive or protected attributes may affect the observed treatments and outcomes. Classification algorithms tasked with predicting outcomes accurately from th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d888fd1b3c70f5f1a91bd7ea877b78c
https://doi.org/10.1145/3287560.3287564
https://doi.org/10.1145/3287560.3287564
Autor:
Felix A. Wichmann, Robert Geirhos, Wieland Brendel, Jörn-Henrik Jacobsen, Matthias Bethge, Claudio Michaelis, Richard S. Zemel
Publikováno v:
Journal of Vision. 20:652
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::536263ad828bf71d848f98f6ad5c5a3f
https://doi.org/10.1167/jov.20.11.652
https://doi.org/10.1167/jov.20.11.652
Publikováno v:
CVPR
We consider learning a distance metric in a weakly supervised setting where bags (or sets) of instances are labeled with bags of labels. A general approach is to formulate the problem as a Multiple Instance Learning (MIL) problem where the metric is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::67a3ddecdb3b9f1c091479fd7d9a7d72
https://doi.org/10.1109/cvpr.2017.630
https://doi.org/10.1109/cvpr.2017.630
Autor:
Richard S. Zemel, Mengye Ren
Publikováno v:
CVPR
While convolutional neural networks have gained impressive success recently in solving structured prediction problems such as semantic segmentation, it remains a challenge to differentiate individual object instances in the scene. Instance segmentati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ede17eabd1723d8682a5223b32e13c8c
https://doi.org/10.1109/cvpr.2017.39
https://doi.org/10.1109/cvpr.2017.39
Publikováno v:
International Journal of Computer Vision. 113:67-79
Tasks that require the synchronization of perception and action are incredibly hard and pose a fundamental challenge to the fields of machine learning and computer vision. One important example of such a task is the problem of performing visual recog
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::973d47371db1bd9c31848742629c7568
https://doi.org/10.1007/s11263-014-0765-x
https://doi.org/10.1007/s11263-014-0765-x
Publikováno v:
Perturbations, Optimization, and Statistics ISBN: 9780262337939
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::60da2d99c075b3f54514771060b60338
https://doi.org/10.7551/mitpress/10761.003.0004
https://doi.org/10.7551/mitpress/10761.003.0004
Autor:
Richard S. Zemel
Publikováno v:
ICMI
Recent advances in computer vision, natural language processing and related areas has led to a renewed interest in artificial intelligence applications spanning multiple domains. Specifically, the generation of natural human-like captions for images
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ae8765fd59604da0772edd0275f3e238
https://doi.org/10.1145/2993148.3011260
https://doi.org/10.1145/2993148.3011260
Publikováno v:
Rep4NLP@ACL
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a5b6b98b2259f9c67bce9c7eb448b68a
https://doi.org/10.18653/v1/w16-1628
https://doi.org/10.18653/v1/w16-1628