Zobrazeno 1 - 10
of 8 630
pro vyhledávání: '"A Eldad"'
In recent years, Graph Neural Networks (GNNs) have been utilized for various applications ranging from drug discovery to network design and social networks. In many applications, it is impossible to observe some properties of the graph directly; inst
Externí odkaz:
http://arxiv.org/abs/2408.10436
Autor:
Bettelheim, Eldad, Meerson, Baruch
Publikováno v:
J. Stat. Mech. (2024) 113204
We combine the Macroscopic Fluctuation Theory and the Inverse Scattering Method to determine the full long-time statistics of the energy density $u(x,t)$ averaged over a given spatial interval, $$U =\frac{1}{2L}\int_{-L}^{L}dx\, u(x,t),$$ in a freely
Externí odkaz:
http://arxiv.org/abs/2407.06335
The large spatial/temporal/frequency scale of geoscience and remote-sensing datasets causes memory issues when using convolutional neural networks for (sub-) surface data segmentation. Recently developed fully reversible or fully invertible networks
Externí odkaz:
http://arxiv.org/abs/2407.00595
This study focuses on inverting time-domain airborne electromagnetic data in 2D by training a neural-network to understand the relationship between data and conductivity, thereby removing the need for expensive forward modeling during the inversion p
Externí odkaz:
http://arxiv.org/abs/2407.00257
Many problems in physical sciences are characterized by the prediction of space-time sequences. Such problems range from weather prediction to the analysis of disease propagation and video prediction. Modern techniques for the solution of these probl
Externí odkaz:
http://arxiv.org/abs/2406.19253
Optimal experimental design is a well studied field in applied science and engineering. Techniques for estimating such a design are commonly used within the framework of parameter estimation. Nonetheless, in recent years parameter estimation techniqu
Externí odkaz:
http://arxiv.org/abs/2406.14003
The integration of Graph Neural Networks (GNNs) and Neural Ordinary and Partial Differential Equations has been extensively studied in recent years. GNN architectures powered by neural differential equations allow us to reason about their behavior, a
Externí odkaz:
http://arxiv.org/abs/2406.10871
Dynamic Positron Emission Tomography (dPET) imaging and Time-Activity Curve (TAC) analyses are essential for understanding and quantifying the biodistribution of radiopharmaceuticals over time and space. Traditional compartmental modeling, while foun
Externí odkaz:
http://arxiv.org/abs/2405.21021
We consider the solution of nonlinear inverse problems where the forward problem is a discretization of a partial differential equation. Such problems are notoriously difficult to solve in practice and require minimizing a combination of a data-fit t
Externí odkaz:
http://arxiv.org/abs/2405.13220
Autor:
Eliasof, Moshe, Haber, Eldad
This paper investigates a link between Graph Neural Networks (GNNs) and Binary Programming (BP) problems, laying the groundwork for GNNs to approximate solutions for these computationally challenging problems. By analyzing the sensitivity of BP probl
Externí odkaz:
http://arxiv.org/abs/2404.04874