Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Raphaël Dang-Nhu"'
Publikováno v:
Frontiers in Computational Neuroscience, Vol 14 (2020)
Natural brains perform miraculously well in learning new tasks from a small number of samples, whereas sample efficient learning is still a major open problem in the field of machine learning. Here, we raise the question, how the neural coding scheme
Externí odkaz:
https://doaj.org/article/ded4e44a9c3b413ab6246d5abc13c36d
Publikováno v:
Frontiers in Computational Neuroscience, 14
Frontiers in Computational Neuroscience, Vol 14 (2020)
Frontiers in Computational Neuroscience
Frontiers in Computational Neuroscience, Vol 14 (2020)
Frontiers in Computational Neuroscience
Natural brains perform miraculously well in learning new tasks from a small number of samples, whereas sample efficient learning is still a major open problem in the field of machine learning. Here, we raise the question, how the neural coding scheme
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a55160285dbfdf472e7f8e98e85fc8a1
https://hdl.handle.net/20.500.11850/470968
https://hdl.handle.net/20.500.11850/470968
Publikováno v:
GECCO
Evolutionary algorithms, being problem-independent and randomized heuristics, are generally believed to be robust to dynamic changes and noisy access to the problem instance. We propose a new method to obtain rigorous runtime results for such setting
Publikováno v:
Proceedings of Machine Learning Research, 119
Proceedings of the 37th International Conference on Machine Learning (ICML 2020)
Proceedings of the 37th International Conference on Machine Learning
ICML 2020 : 37th International Conference on Machine Learning
ICML 2020 : 37th International Conference on Machine Learning, Jul 2020, Vienna (virtual conference), Austria
Proceedings of the 37th International Conference on Machine Learning (ICML 2020)
Proceedings of the 37th International Conference on Machine Learning
ICML 2020 : 37th International Conference on Machine Learning
ICML 2020 : 37th International Conference on Machine Learning, Jul 2020, Vienna (virtual conference), Austria
We develop an effective generation of adversarial attacks on neural models that output a sequence of probability distributions rather than a sequence of single values. This setting includes the recently proposed deep probabilistic autoregressive fore
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9fc5bfa5a2adceda598ea26bd2d4a1c9