Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Nicholas Ampazis"'
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
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::46c2a7cadd0baca513fa70fed0b66c26
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
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::06589f2e1e094c6e0801bd9eff2309b8
https://doi.org/10.1016/j.knosys.2020.105628
https://doi.org/10.1016/j.knosys.2020.105628
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
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b2d37906877d7a5e2821fe47c1ce1ac9
https://doi.org/10.1145/3200947.3201009
https://doi.org/10.1145/3200947.3201009
Publikováno v:
Intelligent Decision Technologies. 9:221-232
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::61a18b6624fa0456aa8a4ff4b1b01bd5
https://doi.org/10.3233/idt-140218
https://doi.org/10.3233/idt-140218
Autor:
Nicholas Ampazis
Publikováno v:
International Journal of Artificial Life Research. 5:56-73
Managing inventory in a multi-level supply chain structure is a difficult task for big retail stores as it is particularly complex to predict demand for the majority of the items. This paper aims to highlight the potential of machine learning approac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c97f9a354308af906df022ee97ddfa3e
https://doi.org/10.4018/ijalr.2015010104
https://doi.org/10.4018/ijalr.2015010104
Publikováno v:
Social Networking. :165-173
In this paper, we examine methods that can provide accurate results in a form of a recommender system within a social networking framework. The social networking site of choice is Twitter, due to its interesting social graph connections and content c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d31cf5b9c7425de8dbd2b7e20daac5d
https://doi.org/10.4236/sn.2013.24016
https://doi.org/10.4236/sn.2013.24016
Publikováno v:
RecSys
With the increase of data collected and computation power available, modern recommender systems are ever facing new challenges. While complex models are developed in academia, industry practice seems to focus on relatively simple techniques that can
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0a22dea9c5712e9b878e38dffa5612c0
https://doi.org/10.1145/2792838.2798715
https://doi.org/10.1145/2792838.2798715
Publikováno v:
Communications in Computer and Information Science ISBN: 9783319120232
SemWebEval@ESWC
SemWebEval@ESWC
In this paper, we report the experiments that we conducted for two of the tasks of the ESWC’14 Challenge on Linked Open Data (LOD)-enabled Recommender Systems. Task 2 and Task 3 dealt with the top-N recommendation problem from a binary user feedbac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9156309d48bb5dd754db1968ebe98a14
https://doi.org/10.1007/978-3-319-12024-9_20
https://doi.org/10.1007/978-3-319-12024-9_20
Publikováno v:
Proceedings of the Ninth International Conference on Dependability and Complex Systems DepCoS-RELCOMEX. June 30 – July 4, 2014, Brunów, Poland ISBN: 9783319070124
DepCoS-RELCOMEX
DepCoS-RELCOMEX
Software systems are becoming essential parts in many products. These are most commonly home devices and other industrial and commercial products. Nowadays, with this increasing dependence on software systems, the size and the complexity of the softw
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::618dc10cedd2f1d373736f31187a90ec
https://doi.org/10.1007/978-3-319-07013-1_38
https://doi.org/10.1007/978-3-319-07013-1_38