Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Chung, Wonchang"'
Autor:
Lacoste, Alexandre, Oreshkin, Boris, Chung, Wonchang, Boquet, Thomas, Rostamzadeh, Negar, Krueger, David
Using variational Bayes neural networks, we develop an algorithm capable of accumulating knowledge into a prior from multiple different tasks. The result is a rich and meaningful prior capable of few-shot learning on new tasks. The posterior can go b
Externí odkaz:
http://arxiv.org/abs/1806.07528
Autor:
Lacoste, Alexandre, Boquet, Thomas, Rostamzadeh, Negar, Oreshkin, Boris, Chung, Wonchang, Krueger, David
The recent literature on deep learning offers new tools to learn a rich probability distribution over high dimensional data such as images or sounds. In this work we investigate the possibility of learning the prior distribution over neural network p
Externí odkaz:
http://arxiv.org/abs/1712.05016
Publikováno v:
In IFAC Proceedings Volumes September 2003 36(20):629-634
Publikováno v:
Proceedings of the 12th International Workshop on Tree Adjoining Grammars and Related Formalisms
12th International Workshop on Tree Adjoining Grammars and Related Formalisms (TAG+12)
12th International Workshop on Tree Adjoining Grammars and Related Formalisms (TAG+12), Jun 2016, Dusseldorf, Germany. pp.85-92
12th International Workshop on Tree Adjoining Grammars and Related Formalisms (TAG+12)
12th International Workshop on Tree Adjoining Grammars and Related Formalisms (TAG+12), Jun 2016, Dusseldorf, Germany. pp.85-92
International audience; We discuss the use of supertags derived from a TAG in transition-based parsing. We show some initial experimental results which suggest that using a representation of a supertag in terms of its structural and linguistic dimens
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::8e9448eab07fad5d61dfc6a400bfd9ba
https://hal.archives-ouvertes.fr/hal-01464845
https://hal.archives-ouvertes.fr/hal-01464845