Guardado en:
Detalles Bibliográficos
Autores principales: Homma, Hikaru, Ohkubo, Jun
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2407.18655
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909390450196480
author Homma, Hikaru
Ohkubo, Jun
author_facet Homma, Hikaru
Ohkubo, Jun
contents The choice of parameters in neural networks is crucial in the performance, and an oracle distribution derived from the ridgelet transform enables us to obtain suitable initial parameters. In other words, the distribution of parameters is connected to the integral representation of target functions. The oracle distribution allows us to avoid the conventional backpropagation learning process; only a linear regression is enough to construct the neural network in simple cases. This study provides a new look at the oracle distributions and ridgelet transforms, i.e., an aspect of importance sampling. In addition, we propose extensions of the parameter sampling methods. We demonstrate the aspect of importance sampling and the proposed sampling algorithms via one-dimensional and high-dimensional examples; the results imply that the magnitude of weight parameters could be more crucial than the intercept parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2407_18655
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Aspects of importance sampling in parameter selection for neural networks using ridgelet transform
Homma, Hikaru
Ohkubo, Jun
Machine Learning
The choice of parameters in neural networks is crucial in the performance, and an oracle distribution derived from the ridgelet transform enables us to obtain suitable initial parameters. In other words, the distribution of parameters is connected to the integral representation of target functions. The oracle distribution allows us to avoid the conventional backpropagation learning process; only a linear regression is enough to construct the neural network in simple cases. This study provides a new look at the oracle distributions and ridgelet transforms, i.e., an aspect of importance sampling. In addition, we propose extensions of the parameter sampling methods. We demonstrate the aspect of importance sampling and the proposed sampling algorithms via one-dimensional and high-dimensional examples; the results imply that the magnitude of weight parameters could be more crucial than the intercept parameters.
title Aspects of importance sampling in parameter selection for neural networks using ridgelet transform
topic Machine Learning
url https://arxiv.org/abs/2407.18655