Zobrazeno 1 - 10
of 1 016
pro vyhledávání: '"A. Cannistraci"'
Deep neural networks often learn similar internal representations, both across different models and within their own layers. While inter-network similarities have enabled techniques such as model stitching and merging, intra-network similarities pres
Externí odkaz:
http://arxiv.org/abs/2410.04941
The growing computational demands posed by increasingly number of neural network's parameters necessitate low-memory-consumption training approaches. Previous memory reduction techniques, such as Low-Rank Adaptation (LoRA) and ReLoRA, suffer from the
Externí odkaz:
http://arxiv.org/abs/2405.15481
Autor:
Crisostomi, Donato, Cannistraci, Irene, Moschella, Luca, Barbiero, Pietro, Ciccone, Marco, Liò, Pietro, Rodolà, Emanuele
Models trained on semantically related datasets and tasks exhibit comparable inter-sample relations within their latent spaces. We investigate in this study the aggregation of such latent spaces to create a unified space encompassing the combined inf
Externí odkaz:
http://arxiv.org/abs/2311.06547
It has been observed that representations learned by distinct neural networks conceal structural similarities when the models are trained under similar inductive biases. From a geometric perspective, identifying the classes of transformations and the
Externí odkaz:
http://arxiv.org/abs/2310.01211
Autor:
Prata, Matteo, Masi, Giuseppe, Berti, Leonardo, Arrigoni, Viviana, Coletta, Andrea, Cannistraci, Irene, Vyetrenko, Svitlana, Velardi, Paola, Bartolini, Novella
The recent advancements in Deep Learning (DL) research have notably influenced the finance sector. We examine the robustness and generalizability of fifteen state-of-the-art DL models focusing on Stock Price Trend Prediction (SPTP) based on Limit Ord
Externí odkaz:
http://arxiv.org/abs/2308.01915
Autor:
Cannistraci, Irene, Moschella, Luca, Maiorca, Valentino, Fumero, Marco, Norelli, Antonio, Rodolà, Emanuele
The use of relative representations for latent embeddings has shown potential in enabling latent space communication and zero-shot model stitching across a wide range of applications. Nevertheless, relative representations rely on a certain amount of
Externí odkaz:
http://arxiv.org/abs/2303.00721
Autor:
Maranghi, Marianna, Anagnostopoulos, Aris, Cannistraci, Irene, Chatzigiannakis, Ioannis, Croce, Federico, Di Teodoro, Giulia, Gentile, Michele, Grani, Giorgio, Lenzerini, Maurizio, Leonardi, Stefano, Mastropietro, Andrea, Palagi, Laura, Pappa, Massimiliano, Rosati, Riccardo, Valentini, Riccardo, Velardi, Paola
The Associazione Medici Diabetologi (AMD) collects and manages one of the largest worldwide-available collections of diabetic patient records, also known as the AMD database. This paper presents the initial results of an ongoing project whose focus i
Externí odkaz:
http://arxiv.org/abs/2206.06182
Autor:
Vergani, Michela1,2 (AUTHOR) m.vergani37@campus.unimib.it, Cannistraci, Rosa2 (AUTHOR), Perseghin, Gianluca1,2 (AUTHOR) gianluca.perseghin@policlinicodimonza.it, Ciardullo, Stefano1,2 (AUTHOR) stefano.ciardullo@unimib.it
Publikováno v:
Journal of Clinical Medicine. Oct2024, Vol. 13 Issue 20, p6225. 16p.
Autor:
Ciardullo, Stefano, Cannistraci, Rosa, Muraca, Emanuele, Zerbini, Francesca, Perseghin, Gianluca
Publikováno v:
In Nutrition, Metabolism and Cardiovascular Diseases April 2024 34(4):963-971
Autor:
Avola, Danilo, Cannistraci, Irene, Cascio, Marco, Cinque, Luigi, Fagioli, Alessio, Foresti, Gian Luca, Rodolà, Emanuele, Solito, Luciana
Publikováno v:
In Computer Methods and Programs in Biomedicine March 2024 245