Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Jean-Marc Marty"'
Publikováno v:
Pattern Recognition
Pattern Recognition, Elsevier, 2019, 91, pp.291-307. ⟨10.1016/j.patcog.2019.02.020⟩
Pattern Recognition, Elsevier, 2019, 91, pp.291-307. ⟨10.1016/j.patcog.2019.02.020⟩
Among the variety of algorithms that have been developed for clustering, prototype-based approaches are very popular due to their low computational complexity, allowing real-life applications. In such algorithms, the data set is summarized by a small
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5c1f71bc8a76636f17fbf4c2cf8eedbb
https://hal.archives-ouvertes.fr/hal-02994817
https://hal.archives-ouvertes.fr/hal-02994817
Publikováno v:
Springer International Publishing
Springer International Publishing, pp.501-510, 2018, ⟨10.1007/978-3-030-01421-6_48⟩
Artificial Neural Networks and Machine Learning – ICANN 2018 ISBN: 9783030014209
ICANN (2)
Springer International Publishing, pp.501-510, 2018, ⟨10.1007/978-3-030-01421-6_48⟩
Artificial Neural Networks and Machine Learning – ICANN 2018 ISBN: 9783030014209
ICANN (2)
The analysis of a dynamic data is challenging. Indeed, the structure of such data changes over time, potentially in a very fast speed. In addition, the objects in such data-sets are often complex. In this paper, our practical motivation is to perform
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d952a7e6ab7e528a77ed1cf28adc09a8
https://hal.archives-ouvertes.fr/hal-02994824
https://hal.archives-ouvertes.fr/hal-02994824
Publikováno v:
EMNLP
We introduce Trans-gram, a simple and computationally-efficient method to simultaneously learn and align wordembeddings for a variety of languages, using only monolingual data and a smaller set of sentence-aligned data. We use our new method to compu