Zobrazeno 1 - 10 of 15 pro vyhledávání: '"Gaëtan Hadjeres"'
1
Quasiconvex Jensen Divergences and Quasiconvex Bregman Divergences
Autor: Gaëtan Hadjeres, Frank Nielsen
Publikováno v: Springer Proceedings in Mathematics & Statistics ISBN: 9783030779566
SPIGL
We first introduce the class of strictly quasiconvex and strictly quasiconcave Jensen divergences which are asymmetric distances, and study some of their properties. We then define the strictly quasiconvex Bregman divergences as the limit case of sca
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::cb5dd959283f50597f13ba6f80c007b1
https://doi.org/10.1007/978-3-030-77957-3_11
Zobrazit plný text záznamu
2
Anticipation-RNN: enforcing unary constraints in sequence generation, with application to interactive music generation
Autor: Gaëtan Hadjeres, Frank Nielsen
Publikováno v: Neural Computing and Applications. 32:995-1005
Recurrent neural networks (RNNs) are now widely used on sequence generation tasks due to their ability to learn long-range dependencies and to generate sequences of arbitrary length. However, their left-to-right generation procedure only allows a lim
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::973add9dfb71f7ab7ef01a5185037978
https://doi.org/10.1007/s00521-018-3868-4
Zobrazit plný text záznamu
3
Machine learning research that matters for music creation: A case study
Autor: Úna Monaghan, Bob L. Sturm, Oded Ben-Tal, François Pachet, Emmanuel Deruty, Gaëtan Hadjeres, Nick Collins, Dorien Herremans, Elaine Chew
Publikováno v: Journal of New Music Research
Journal of New Music Research, Taylor & Francis (Routledge), 2019, 48 (1), pp.36-55. ⟨10.1080/09298215.2018.1515233⟩
International audience; Research applying machine learning to music modeling and generation typically proposes model architectures, training methods and datasets, and gauges system performance using quantitative measures like sequence likelihoods and
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fa5eeff29bfef76224a21c6e57364496
https://doi.org/10.1080/09298215.2018.1515233
Zobrazit plný text záznamu
10
Challenge and Strategy
Autor: François-David Pachet, Gaëtan Hadjeres, Jean-Pierre Briot
Publikováno v: Deep Learning Techniques for Music Generation ISBN: 9783319701622
We are now reaching the core of this book. This chapter will analyze in depth how to apply the architectures presented in Chapter 5 to learn and generate music. We will first start with a naive, straightforward strategy, using the basic prediction ta
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::72a9ae1e2f1fb48276f86d8fa54a012e
https://doi.org/10.1007/978-3-319-70163-9_6
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje