Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Flora Sakketou"'
Publikováno v:
Proceedings of the Tenth International Workshop on Natural Language Processing for Social Media.
Publikováno v:
Machine Learning and Knowledge Extraction
Volume 1
Issue 3
Pages 53-944
Volume 1
Issue 3
Pages 53-944
In recent years the emergence of social media has become more prominent than ever. Social networking has become the de facto tool used by people all around the world for information discovery. Consequently, the importance of recommendations in a soci
Autor:
Flora Sakketou, Nicholas Ampazis
Publikováno v:
Knowledge-Based Systems. 195:105628
GloVe representations of words as vector embeddings in continuous spaces are learned from matrix factorization of the words’ co-occurrences matrix constructed from large corpora. Due to their high quality as textual features, GloVe embeddings have
Autor:
Flora Sakketou, Nicholas Ampazis
Publikováno v:
IFIP Advances in Information and Communication Technology ISBN: 9783030198220
AIAI
IFIP Advances in Information and Communication Technology
15th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI)
15th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2019, Hersonissos, Greece. pp.673-685, ⟨10.1007/978-3-030-19823-7_56⟩
AIAI
IFIP Advances in Information and Communication Technology
15th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI)
15th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2019, Hersonissos, Greece. pp.673-685, ⟨10.1007/978-3-030-19823-7_56⟩
Part 13: Recommendation Systems; International audience; In a number of recent studies the Scaled Exponential Linear Unit (SELU) activation function has been shown to automatically regularize network parameters and to make learning robust due to its
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a14d14e2fe76d0eca248eb2a2707ed8e
https://doi.org/10.1007/978-3-030-19823-7_56
https://doi.org/10.1007/978-3-030-19823-7_56
Publikováno v:
SETN
Collaborative filtering recommender systems make automatic predictions about users' interests by utilizing information collected from similarly minded users in order to recommend new items. However in most practical settings the ratings matrix is ext