Guardado en:
Detalles Bibliográficos
Autores principales: Furuya, Takashi, Suetake, Kazuma, Taniguchi, Koichi, Kusumoto, Hiroyuki, Saiin, Ryuji, Daimon, Tomohiro
Formato: Preprint
Publicado: 2021
Materias:
Acceso en línea:https://arxiv.org/abs/2105.10832
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911807790120960
author Furuya, Takashi
Suetake, Kazuma
Taniguchi, Koichi
Kusumoto, Hiroyuki
Saiin, Ryuji
Daimon, Tomohiro
author_facet Furuya, Takashi
Suetake, Kazuma
Taniguchi, Koichi
Kusumoto, Hiroyuki
Saiin, Ryuji
Daimon, Tomohiro
contents Recurrent neural networks (RNNs) are a class of neural networks used in sequential tasks. However, in general, RNNs have a large number of parameters and involve enormous computational costs by repeating the recurrent structures in many time steps. As a method to overcome this difficulty, RNN pruning has attracted increasing attention in recent years, and it brings us benefits in terms of the reduction of computational cost as the time step progresses. However, most existing methods of RNN pruning are heuristic. The purpose of this paper is to study the theoretical scheme for RNN pruning method. We propose an appropriate pruning algorithm for RNNs inspired by "spectral pruning", and provide the generalization error bounds for compressed RNNs. We also provide numerical experiments to demonstrate our theoretical results and show the effectiveness of our pruning method compared with existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2105_10832
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Spectral Pruning for Recurrent Neural Networks
Furuya, Takashi
Suetake, Kazuma
Taniguchi, Koichi
Kusumoto, Hiroyuki
Saiin, Ryuji
Daimon, Tomohiro
Machine Learning
Recurrent neural networks (RNNs) are a class of neural networks used in sequential tasks. However, in general, RNNs have a large number of parameters and involve enormous computational costs by repeating the recurrent structures in many time steps. As a method to overcome this difficulty, RNN pruning has attracted increasing attention in recent years, and it brings us benefits in terms of the reduction of computational cost as the time step progresses. However, most existing methods of RNN pruning are heuristic. The purpose of this paper is to study the theoretical scheme for RNN pruning method. We propose an appropriate pruning algorithm for RNNs inspired by "spectral pruning", and provide the generalization error bounds for compressed RNNs. We also provide numerical experiments to demonstrate our theoretical results and show the effectiveness of our pruning method compared with existing methods.
title Spectral Pruning for Recurrent Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2105.10832