Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Vivek Ramavajjala"'
Publikováno v:
WSDM
Label propagation is a powerful and flexible semi-supervised learning technique on graphs. Neural networks, on the other hand, have proven track records in many supervised learning tasks. In this work, we propose a training framework with a graph-reg
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c7e48a73f63af03e7e8238860988a46f
https://doi.org/10.1145/3159652.3159731
https://doi.org/10.1145/3159652.3159731
Publikováno v:
WWW
We introduce the problem of automatically suggesting conversational responses to photos and present an intelligent assistant called PhotoReply that solves the problem in the context of a messaging application. For example, when a user receives a phot
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dbe7170e46e212f8abfe3774f7ae7dbf
https://doi.org/10.1145/3178876.3186164
https://doi.org/10.1145/3178876.3186164
Autor:
Sujith Ravi, Tobias Kaufmann, Karol Kurach, Balint Miklos, Marina Ganea, László Lukács, Andrew Tomkins, Vivek Ramavajjala, Greg S. Corrado, Peter Young, Anjuli Kannan
Publikováno v:
KDD
In this paper we propose and investigate a novel end-to-end method for automatically generating short email responses, called Smart Reply. It generates semantically diverse suggestions that can be used as complete email responses with just one tap on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c39f7aae93e1a7bbf7f45187009c7f3
Autor:
Charles Elkan, Vivek Ramavajjala
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783642334856
ECML/PKDD (2)
ECML/PKDD (2)
This paper investigates a reinforcement learning method that combines learning a model of the environment with least-squares policy iteration (LSPI). The LSPI algorithm learns a linear approximation of the optimal state-action value function; the ide
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4bceb1b7acf9339e2d2253459c20e749
https://doi.org/10.1007/978-3-642-33486-3_14
https://doi.org/10.1007/978-3-642-33486-3_14