Zobrazeno 1 - 10
of 771
pro vyhledávání: '"Hidalgo, Javier"'
Modern machine learning systems are increasingly trained on large amounts of data embedded in high-dimensional spaces. Often this is done without analyzing the structure of the dataset. In this work, we propose a framework to study the geometric stru
Externí odkaz:
http://arxiv.org/abs/2210.17475
Processing 3D pointclouds with Deep Learning methods is not an easy task. A common choice is to do so with Graph Neural Networks, but this framework involves the creation of edges between points, which are explicitly not related between them. Histori
Externí odkaz:
http://arxiv.org/abs/2209.00949
This work presents SkinningNet, an end-to-end Two-Stream Graph Neural Network architecture that computes skinning weights from an input mesh and its associated skeleton, without making any assumptions on shape class and structure of the provided mesh
Externí odkaz:
http://arxiv.org/abs/2203.04746
We derive a risk lower bound in estimating the threshold parameter without knowing whether the threshold regression model is continuous or not. The bound goes to zero as the sample size $ n $ grows only at the cube root rate. Motivated by this findin
Externí odkaz:
http://arxiv.org/abs/2203.00349
Autor:
Villa-Mancera, Abel1 (AUTHOR) abel.villa@gmail.com, Maldonado-Hidalgo, Javier1 (AUTHOR) manuel.roblesr@correo.buap.mx, Robles-Robles, Manuel1 (AUTHOR) jose.rodriguez@correo.buap.mx, Olivares-Pérez, Jaime2 (AUTHOR) olivaares@hotmail.com, Olmedo-Juárez, Agustín3 (AUTHOR) aolmedoj@gmail.com, Rodríguez-Castillo, José1 (AUTHOR) noemi.perezmen@correo.buap.mx, Pérez-Mendoza, Noemi1 (AUTHOR) fernando.utrera@correo.buap.mx, Utrera-Quintana, Fernando1 (AUTHOR) samuel.ortega@correo.buap.mx, Pérez, José4 (AUTHOR) an1pearj@uco.es, Ortega-Vargas, Samuel1 (AUTHOR)
Publikováno v:
International Journal of Molecular Sciences. Jul2024, Vol. 25 Issue 13, p7225. 16p.
Feature spaces in the deep layers of convolutional neural networks (CNNs) are often very high-dimensional and difficult to interpret. However, convolutional layers consist of multiple channels that are activated by different types of inputs, which su
Externí odkaz:
http://arxiv.org/abs/2110.11400
In a beyond-5G (B5G) scenario, we consider a virtual private mobile network (VPMN), i.e., a set of user equipments (UEs) directly communicating in a device-to-device (D2D) fashion, and connected to the cellular network by multiple gateways. The purpo
Externí odkaz:
http://arxiv.org/abs/2110.01195
State-of-the-art neural network architectures continue to scale in size and deliver impressive generalization results, although this comes at the expense of limited interpretability. In particular, a key challenge is to determine when to stop trainin
Externí odkaz:
http://arxiv.org/abs/2107.12972
Publikováno v:
Essays in Honor of Joon Y. Park: Econometric Theory