Zobrazeno 1 - 10
of 8 059
pro vyhledávání: '"Montufar, A"'
Autor:
Ana Marie R. Abante
Publikováno v:
International Journal of Computing Sciences Research, Vol 6, Pp 741-762 (2022)
Purpose – The paper aims to generate analytical data to reintroduce the geographic naming based on the existing coastwise feature names as part of contextualizing the ecosystem relative to risk reality phenomena that are based on the actual land an
Externí odkaz:
https://doaj.org/article/cde7fc4bec9d4fcc81f298e992941623
Autor:
Liang, Shuang, Montúfar, Guido
We examine the implicit bias of mirror flow in univariate least squares error regression with wide and shallow neural networks. For a broad class of potential functions, we show that mirror flow exhibits lazy training and has the same implicit bias a
Externí odkaz:
http://arxiv.org/abs/2410.03988
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Proaño Lucero, Gabriela Elizabeth, Serrano Castillo, Byron Jesús, Maldonado Arias, Diego Fabián, Castillo Montalvan, Lourdes Nayeli, Sánchez Orta, Josselin Mishell
Publikováno v:
Tesla Revista Científica; ene-jun2024, Vol. 4 Issue 1, p1-19, 19p
Bounds on the smallest eigenvalue of the neural tangent kernel (NTK) are a key ingredient in the analysis of neural network optimization and memorization. However, existing results require distributional assumptions on the data and are limited to a h
Externí odkaz:
http://arxiv.org/abs/2405.14630
Autor:
Hawkins, Timothy
Publikováno v:
The Historian, 2002 Apr 01. 64(3/4), 513-533.
Externí odkaz:
https://www.jstor.org/stable/24451018
Autor:
Aguirre Salvador, Rodolfo1
Publikováno v:
Temas Americanistas. dic2019, Issue 43, p160-188. 29p. 1 Chart.
Kakade's natural policy gradient method has been studied extensively in the last years showing linear convergence with and without regularization. We study another natural gradient method which is based on the Fisher information matrix of the state-a
Externí odkaz:
http://arxiv.org/abs/2403.19448
We consider a binary classifier defined as the sign of a tropical rational function, that is, as the difference of two convex piecewise linear functions. The parameter space of ReLU neural networks is contained as a semialgebraic set inside the param
Externí odkaz:
http://arxiv.org/abs/2403.11871
The problem of benign overfitting asks whether it is possible for a model to perfectly fit noisy training data and still generalize well. We study benign overfitting in two-layer leaky ReLU networks trained with the hinge loss on a binary classificat
Externí odkaz:
http://arxiv.org/abs/2403.06903