Zobrazeno 1 - 10
of 139
pro vyhledávání: '"Valenti, Andrea"'
Graphs can be leveraged to model polyphonic multitrack symbolic music, where notes, chords and entire sections may be linked at different levels of the musical hierarchy by tonal and rhythmic relationships. Nonetheless, there is a lack of works that
Externí odkaz:
http://arxiv.org/abs/2307.14928
While showing impressive performance on various kinds of learning tasks, it is yet unclear whether deep learning models have the ability to robustly tackle reasoning tasks. than by learning the underlying reasoning process that is actually required t
Externí odkaz:
http://arxiv.org/abs/2210.02095
Autor:
Valenti, Andrea, Bacciu, Davide
The recently introduced weakly disentangled representations proposed to relax some constraints of the previous definitions of disentanglement, in exchange for more flexibility. However, at the moment, weak disentanglement can only be achieved by incr
Externí odkaz:
http://arxiv.org/abs/2209.05336
Autor:
Valenti, Andrea, Bacciu, Davide
Disentanglement is a difficult property to enforce in neural representations. This might be due, in part, to a formalization of the disentanglement problem that focuses too heavily on separating relevant factors of variation of the data in single iso
Externí odkaz:
http://arxiv.org/abs/2205.10056
The polyphonic nature of music makes the application of deep learning to music modelling a challenging task. On the other hand, the Transformer architecture seems to be a good fit for this kind of data. In this work, we present Calliope, a novel auto
Externí odkaz:
http://arxiv.org/abs/2107.05546
Typical EEG-based BCI applications require the computation of complex functions over the noisy EEG channels to be carried out in an efficient way. Deep learning algorithms are capable of learning flexible nonlinear functions directly from data, and t
Externí odkaz:
http://arxiv.org/abs/2008.13485
We address the challenging open problem of learning an effective latent space for symbolic music data in generative music modeling. We focus on leveraging adversarial regularization as a flexible and natural mean to imbue variational autoencoders wit
Externí odkaz:
http://arxiv.org/abs/2001.05494
Autor:
Trovato, Maria1 (AUTHOR) mariatrovato@tin.it, Valenti, Andrea1 (AUTHOR)
Publikováno v:
Diagnostics (2075-4418). Jun2023, Vol. 13 Issue 12, p2114. 19p.
Autor:
Ruffino, Roberta, Fichera, Luca, Valenti, Andrea, Jankowski, Maciej, Konovalov, Oleg, Messina, Grazia M.L., Licciardello, Antonino, Tuccitto, Nunzio, Li-Destri, Giovanni, Marletta, Giovanni
Publikováno v:
In Polymer 16 September 2021 230
Publikováno v:
In Heart & Lung July-August 2020 49(4):407-414