Zobrazeno 1 - 10
of 245
pro vyhledávání: '"Peter Morales"'
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Applied Network Science, Vol 6, Iss 1, Pp 1-20 (2021)
Abstract Complex networks are often either too large for full exploration, partially accessible, or partially observed. Downstream learning tasks on these incomplete networks can produce low quality results. In addition, reducing the incompleteness o
Externí odkaz:
https://doaj.org/article/d9c0c54179f54365aeb9ff7985ad5fe9
Publikováno v:
Journal of Artificial Intelligence Research. 73:821-846
We present a scalable tree search planning algorithm for large multi-agent sequential decision problems that require dynamic collaboration. Teams of agents need to coordinate decisions in many domains, but naive approaches fail due to the exponential
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3782a2645943b03666b7f72287133e65
https://doi.org/10.1613/jair.1.13261
https://doi.org/10.1613/jair.1.13261
Autor:
Ashraful Islam, Ben Lundell, Harpreet Sawhney, Sudipta N. Sinha, Peter Morales, Richard J. Radke
We present a self-supervised learning (SSL) method suitable for semi-global tasks such as object detection and semantic segmentation. We enforce local consistency between self-learned features, representing corresponding image locations of transforme
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8e757c369494d59105240eceeb1997fa
Publikováno v:
Applied Network Science, Vol 6, Iss 1, Pp 1-20 (2021)
Complex networks are often either too large for full exploration, partially accessible, or partially observed. Downstream learning tasks on these incomplete networks can produce low quality results. In addition, reducing the incompleteness of the net
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f30895ac61ed0905ad97820fbfb9489d
https://doi.org/10.1007/s41109-021-00365-8
https://doi.org/10.1007/s41109-021-00365-8
Publikováno v:
HPEC
Some of the most important publications in deep reinforcement learning over the last few years have been fueled by access to massive amounts of computation through large scale distributed systems. The success of these approaches in achieving human-ex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2a0c4e36bb499a0210a10e904f561ea1
https://doi.org/10.1109/hpec43674.2020.9286212
https://doi.org/10.1109/hpec43674.2020.9286212
Autor:
Nicholas B. Evans, Peter Morales, Kwanghun Chung, Tzofi Klinghoffer, Young Gyun Park, Laura J. Brattain
Publikováno v:
CVPR Workshops
arXiv
arXiv
Existing learning-based methods to automatically trace axons in 3D brain imagery often rely on manually annotated segmentation labels. Labeling is a labor-intensive process and is not scalable to whole-brain analysis, which is needed for improved und
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0e23b4c51977e290ef91e048efecd8f3
https://doi.org/10.1109/cvprw50498.2020.00497
https://doi.org/10.1109/cvprw50498.2020.00497
Publikováno v:
Complex Networks and Their Applications VIII ISBN: 9783030366865
COMPLEX NETWORKS (1)
COMPLEX NETWORKS (1)
Complex networks are often either too large for full exploration, partially accessible, or partially observed. Downstream learning tasks on these incomplete networks can produce low quality results. In addition, reducing the incompleteness of the net
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0a944e5457d71eb0168f958bc2fabd49
https://doi.org/10.1007/978-3-030-36687-2_75
https://doi.org/10.1007/978-3-030-36687-2_75
Publikováno v:
CVPR Workshops
Haze degrades content and obscures information of images, which can negatively impact vision-based decision-making in real-time systems. In this paper, we propose an efficient fully convolutional neural network (CNN) image dehazing method designed to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::73e5a28cc1ff542e490a9368788ef97b
https://doi.org/10.1109/cvprw.2019.00260
https://doi.org/10.1109/cvprw.2019.00260