Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Yeonjong Shin"'
Autor:
SANGHYUN LEE, YEONJONG SHIN
Publikováno v:
SIAM Journal on Scientific Computing; 2024, Vol. 46 Issue 4, pC273-C296, 24p
Autor:
LAUZON, JESSICA T., SIU WUN CHEUNG, YEONJONG SHIN, YOUNGSOO CHOI, COPELAND, DYLAN M., HUYNH, KEVIN
Publikováno v:
SIAM Journal on Scientific Computing; 2024, Vol. 46 Issue 4, pB474-B501, 28p
Publikováno v:
Neural Networks. 161:185-201
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef60a18999f3642cfc00c01142f88906
https://doi.org/10.1016/j.neunet.2023.01.002
https://doi.org/10.1016/j.neunet.2023.01.002
Autor:
Mark Ainsworth, Yeonjong Shin
Publikováno v:
SIAM Journal on Scientific Computing. 44:A2253-A2275
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8a1125508bade806bffa8b0eff0a4e47
https://doi.org/10.1137/21m1460764
https://doi.org/10.1137/21m1460764
Publikováno v:
Philosophical transactions. Series A, Mathematical, physical, and engineering sciences. 380(2229)
We propose the GENERIC formalism informed neural networks (GFINNs) that obey the symmetric degeneracy conditions of the GENERIC formalism. GFINNs comprise two modules, each of which contains two components. We model each component using a neural netw
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::df1aea88f40f2dc7c7bd37c9a0e51a42
https://pubmed.ncbi.nlm.nih.gov/35719066
https://pubmed.ncbi.nlm.nih.gov/35719066
Publikováno v:
Neural networks : the official journal of the International Neural Network Society. 153
We present the analysis of approximation rates of operator learning in Chen and Chen (1995) and Lu et al. (2021), where continuous operators are approximated by a sum of products of branch and trunk networks. In this work, we consider the rates of le
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c5dea052448b099c3a2ca0b969cd6479
https://pubmed.ncbi.nlm.nih.gov/35803112
https://pubmed.ncbi.nlm.nih.gov/35803112
We propose a new type of neural networks, Kronecker neural networks (KNNs), that form a general framework for neural networks with adaptive activation functions. KNNs employ the Kronecker product, which provides an efficient way of constructing a ver
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::696ff02a261f0ba8aeec09001b3d7554
Autor:
AINSWORTH, MARK, YEONJONG SHIN
Publikováno v:
SIAM Journal on Scientific Computing; 2022, Vol. 44 Issue 4, pA2253-A2275, 23p
Autor:
Yeonjong Shin, Mark Ainsworth
The ability of neural networks to provide `best in class' approximation across a wide range of applications is well-documented. Nevertheless, the powerful expressivity of neural networks comes to naught if one is unable to effectively train (choose)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c1c7881797e97e697f54d1553bd05043
Publikováno v:
Journal of Computational Physics. 371:363-381
We present a sequential method for approximating an unknown function sequentially using random noisy samples. Unlike the traditional function approximation methods, the current method constructs the approximation using one sample at a time. This resu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f49cf02e10bf713e6387f9c9b985ffe9
https://doi.org/10.1016/j.jcp.2018.05.042
https://doi.org/10.1016/j.jcp.2018.05.042