Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Konrad Zolna"'
Autor:
Leonard Boussioux, Dzmitry Bahdanau, Yoshua Bengio, Konrad Zolna, Maxime Chevalier-Boisvert, David Yu-Tung Hui, Chitwan Saharia
Publikováno v:
IJCNN
In adversarial imitation learning, a discriminator is trained to differentiate agent episodes from expert demonstrations representing the desired behavior. However, as the trained policy learns to be more successful, the negative examples (the ones p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2a5e09505f176b5b3d9a2d853fbbd022
http://arxiv.org/abs/2002.00412
http://arxiv.org/abs/2002.00412
Autor:
Misha Denil, David J. Barker, Sergio Gomez Colmenarejo, Ziyu Wang, Nando de Freitas, Ksenia Konyushova, Mel Vecerik, Serkan Cabi, David Budden, Jonathan Scholz, Alexander Novikov, Scott Reed, Yusuf Aytar, Oleg P. Sushkov, Rae Jeong, Konrad Zolna
Publikováno v:
Robotics: Science and Systems
We present a framework for data-driven robotics that makes use of a large dataset of recorded robot experience and scales to several tasks using learned reward functions. We show how to apply this framework to accomplish three different object manipu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::949a18797a593e4bc0f952ace525ffc7
Publikováno v:
Mechanical Systems and Signal Processing. 75:94-108
The paper presents the homoscedastic nonlinear cointegration. The method leads to stable variances in nonlinear cointegration residuals. The adapted Breusch–Pagan test procedure is developed to test for the presence of heteroscedasticity (or homosc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::03e43b85e0e542c70ba9ce41bd7b7b7a
https://doi.org/10.1016/j.ymssp.2015.12.014
https://doi.org/10.1016/j.ymssp.2015.12.014
Publikováno v:
AAAI
Currently available methods for extracting saliency maps identify parts of the input which are the most important to a specific fixed classifier. We show that this strong dependence on a given classifier hinders their performance. To address this pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d11ba8873e6726025025e1b8d7f22bd3
http://arxiv.org/abs/1805.08249
http://arxiv.org/abs/1805.08249
Publikováno v:
AAAI
Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly modifying most of its pixels, or by occluding it with a patch. In this paper, we propose a method that keeps the image
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::10554dc57c353af2965c504815d7aa1f
https://doi.org/10.1609/aaai.v33i01.330110077
https://doi.org/10.1609/aaai.v33i01.330110077
Autor:
Konrad Zolna
Publikováno v:
IJCNN
The method presented extends a given regression neural network to make its performance improve. The modification affects the learning procedure only, hence the extension may be easily omitted during evaluation without any change in prediction. It mea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f3dbdc69dd621dc3f4a66670d20f7ac
https://doi.org/10.1109/ijcnn.2017.7966164
https://doi.org/10.1109/ijcnn.2017.7966164
Publikováno v:
Mathematical Problems in Engineering, Vol 2015 (2015)
Monitoring of trends and removal of undesired trends from operational/process parameters in wind turbines is important for their condition monitoring. This paper presents the homoscedastic nonlinear cointegration for the solution to this problem. The
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34f15b796f8fddd93ee9b38d8e764deb
https://doaj.org/article/4f3ff3a444d94204bc0dd30a80eda057
https://doaj.org/article/4f3ff3a444d94204bc0dd30a80eda057