Zobrazeno 1 - 10
of 7 035
pro vyhledávání: '"Cini, A"'
In processing multiple time series, accounting for the individual features of each sequence can be challenging. To address this, modern deep learning methods for time series analysis combine a shared (global) model with local layers, specific to each
Externí odkaz:
http://arxiv.org/abs/2410.14630
Entanglement and quantum correlations between atoms are not usually considered key ingredients of the superradiant phase transition. Here we consider the Tavis-Cummings model, a solvable system of two-levels atoms, coupled with a single-mode quantize
Externí odkaz:
http://arxiv.org/abs/2404.19373
Virtual sensing techniques allow for inferring signals at new unmonitored locations by exploiting spatio-temporal measurements coming from physical sensors at different locations. However, as the sensor coverage becomes sparse due to costs or other c
Externí odkaz:
http://arxiv.org/abs/2402.12598
Graph-based deep learning methods have become popular tools to process collections of correlated time series. Differently from traditional multivariate forecasting methods, neural graph-based predictors take advantage of pairwise relationships by con
Externí odkaz:
http://arxiv.org/abs/2310.15978
Relationships among time series can be exploited as inductive biases in learning effective forecasting models. In hierarchical time series, relationships among subsets of sequences induce hard constraints (hierarchical inductive biases) on the predic
Externí odkaz:
http://arxiv.org/abs/2305.19183
Graph-based representations and message-passing modular policies constitute prominent approaches to tackling composable control problems in reinforcement learning (RL). However, as shown by recent graph deep learning literature, such local message-pa
Externí odkaz:
http://arxiv.org/abs/2304.05099
Autor:
Rachael Frost, Silvy Mathew, Verity Thomas, Sayem Uddin, Adriana Salame, Christine Vial, Tanya Cohen, Sukvinder Kaur Bhamra, Juan Carlos Bazo Alvarez, Cini Bhanu, Michael Heinrich, Kate Walters
Publikováno v:
BMC Complementary Medicine and Therapies, Vol 24, Iss 1, Pp 1-20 (2024)
Abstract Background Depression, anxiety, and insomnia are prevalent in older people and are associated with increased risk of mortality, dependency, falls and reduced quality of life. Prior to or whilst seeking treatment, older people often manage th
Externí odkaz:
https://doaj.org/article/b6f6e81cd0ef481e82930982d794f749
Autor:
A. Mazzeo, M. Uliano, P. Mucci, M. Penzotti, L. Angelini, F. Cini, L. Craighero, M. Controzzi
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-13 (2024)
Abstract Robotic literature widely addresses deformable object manipulation, but few studies analyzed human manipulation accounting for different levels of deformability and task properties. We asked participants to grasp and insert rigid and deforma
Externí odkaz:
https://doaj.org/article/35aaa0aa304f47f1a1cf03377af18c60
Publikováno v:
Transactions on Machine Learning Research. https://openreview.net/forum?id=7kWjB9zW90
Conditioning image generation on specific features of the desired output is a key ingredient of modern generative models. However, existing approaches lack a general and unified way of representing structural and semantic conditioning at diverse gran
Externí odkaz:
http://arxiv.org/abs/2303.14681
Spatiotemporal graph neural networks have shown to be effective in time series forecasting applications, achieving better performance than standard univariate predictors in several settings. These architectures take advantage of a graph structure and
Externí odkaz:
http://arxiv.org/abs/2302.04071