Zobrazeno 1 - 10
of 58
pro vyhledávání: '"Malagò, Luigi"'
We focus on automatic feature extraction for raw audio heartbeat sounds, aimed at anomaly detection applications in healthcare. We learn features with the help of an autoencoder composed by a 1D non-causal convolutional encoder and a WaveNet decoder
Externí odkaz:
http://arxiv.org/abs/2102.12289
Markov Chain Monte Carlo (MCMC) algorithms are commonly used for their versatility in sampling from complicated probability distributions. However, as the dimension of the distribution gets larger, the computational costs for a satisfactory explorati
Externí odkaz:
http://arxiv.org/abs/2011.14276
Publikováno v:
International Journal of Geometric Methods in Modern Physics, 2022, 2250214
We provide an Information-Geometric formulation of Classical Mechanics on the Riemannian manifold of probability distributions, which is an affine manifold endowed with a dually-flat connection. In a non-parametric formalism, we consider the full set
Externí odkaz:
http://arxiv.org/abs/2009.09431
Bayesian Neural Networks (BNNs) often result uncalibrated after training, usually tending towards overconfidence. Devising effective calibration methods with low impact in terms of computational complexity is thus of central interest. In this paper w
Externí odkaz:
http://arxiv.org/abs/2008.06729
Helmholtz Machines (HMs) are a class of generative models composed of two Sigmoid Belief Networks (SBNs), acting respectively as an encoder and a decoder. These models are commonly trained using a two-step optimization algorithm called Wake-Sleep (WS
Externí odkaz:
http://arxiv.org/abs/2008.06687
Anomaly detection for Magnetic Resonance Images (MRIs) can be solved with unsupervised methods by learning the distribution of healthy images and identifying anomalies as outliers. In presence of an additional dataset of unlabelled data containing al
Externí odkaz:
http://arxiv.org/abs/2007.12528
Publikováno v:
Mach. Learn.: Sci. Technol. 1 035014, 2020
The next generation 21 cm surveys open a new window onto the early stages of cosmic structure formation and provide new insights about the Epoch of Reionization (EoR). However, the non-Gaussian nature of the 21 cm signal along with the huge amount of
Externí odkaz:
http://arxiv.org/abs/2005.07694
Upcoming experiments such as Hydrogen Epoch of Reionization Array (HERA) and Square Kilometre Array (SKA) are intended to measure the 21cm signal over a wide range of redshifts, representing an incredible opportunity in advancing our understanding ab
Externí odkaz:
http://arxiv.org/abs/2005.02299
Autor:
Volpi, Riccardo, Malagò, Luigi
Learning an embedding for a large collection of items is a popular approach to overcome the computational limitations associated to one-hot encodings. The aim of item embedding is to learn a low dimensional space for the representations, able to capt
Externí odkaz:
http://arxiv.org/abs/1912.02280
Publikováno v:
Phys. Rev. D 102, 103509 (2020)
In this paper, we present the first study that compares different models of Bayesian Neural Networks (BNNs) to predict the posterior distribution of the cosmological parameters directly from the Cosmic Microwave Background temperature and polarizatio
Externí odkaz:
http://arxiv.org/abs/1911.08508