Uncertainty propagation for dropout-based Bayesian neural networks.

Mae, Yuki; Kumagai, Wataru; Kanamori, Takafumi

Mae, Yuki; Kumagai, Wataru; Kanamori, Takafumi.

Afiliação

Mae Y; DENSO CORPORATION, 1-1, Showa-cho, Kariya, Aichi, 448-8661, Japan. Electronic address: yuki.mae.j5w@jp.denso.com.
Kumagai W; Graduate School of Engineering, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8654, Japan; Center for Advanced Intelligence Project, RIKEN, Nihonbashi 1-chome Mitsui Building, 15th floor,1-4-1 Nihonbashi, Chuo-ku, Tokyo, 103-0027, Japan. Electronic address: kumagai@weblab.t.u-tokyo.ac.jp.
Kanamori T; Department of Mathematical and Computing Science, Tokyo Institute of Technology, 2-12-1 Ookayama, Meguro-ku, Tokyo, 152-8552, Japan; Center for Advanced Intelligence Project, RIKEN, Nihonbashi 1-chome Mitsui Building, 15th floor,1-4-1 Nihonbashi, Chuo-ku, Tokyo, 103-0027, Japan. Electronic address: kanamori@c.titech.ac.jp.

Neural Netw ; 144: 394-406, 2021 Dec.

Article em En | MEDLINE | ID: mdl-34562813

Assuntos

Redes Neurais de Computação; Teorema de Bayes; Método de Monte Carlo; Reprodutibilidade dos Testes; Incerteza

Palavras-chave

LSTM; Out-of-distribution; Sampling-free method; Uncertainty evaluation; Variance propagation

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Redes Neurais de Computação Tipo de estudo: Health_economic_evaluation / Prognostic_studies Idioma: En Ano de publicação: 2021 Tipo de documento: Article

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google