FastLRNR and Sparse Physics Informed Backpropagation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Cho, Woojin, Lee, Kookjin, Park, Noseong, Rim, Donsub, Welper, Gerrit
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911375452798976
author Cho, Woojin
Lee, Kookjin
Park, Noseong
Rim, Donsub
Welper, Gerrit
author_facet Cho, Woojin
Lee, Kookjin
Park, Noseong
Rim, Donsub
Welper, Gerrit
contents We introduce Sparse Physics Informed Backpropagation (SPInProp), a new class of methods for accelerating backpropagation for a specialized neural network architecture called Low Rank Neural Representation (LRNR). The approach exploits the low rank structure within LRNR and constructs a reduced neural network approximation that is much smaller in size. We call the smaller network FastLRNR. We show that backpropagation of FastLRNR can be substituted for that of LRNR, enabling a significant reduction in complexity. We apply SPInProp to a physics informed neural networks framework and demonstrate how the solution of parametrized partial differential equations is accelerated.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04001
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FastLRNR and Sparse Physics Informed Backpropagation
Cho, Woojin
Lee, Kookjin
Park, Noseong
Rim, Donsub
Welper, Gerrit
Machine Learning
Artificial Intelligence
Numerical Analysis
68T07, 65D25, 65M22
We introduce Sparse Physics Informed Backpropagation (SPInProp), a new class of methods for accelerating backpropagation for a specialized neural network architecture called Low Rank Neural Representation (LRNR). The approach exploits the low rank structure within LRNR and constructs a reduced neural network approximation that is much smaller in size. We call the smaller network FastLRNR. We show that backpropagation of FastLRNR can be substituted for that of LRNR, enabling a significant reduction in complexity. We apply SPInProp to a physics informed neural networks framework and demonstrate how the solution of parametrized partial differential equations is accelerated.
title FastLRNR and Sparse Physics Informed Backpropagation
topic Machine Learning
Artificial Intelligence
Numerical Analysis
68T07, 65D25, 65M22
url https://arxiv.org/abs/2410.04001