JSAI2022

Presentation information

General Session

General Session » GS-2 Machine learning

[1D1-GS-2] Machine learning: algorithm

Tue. Jun 14, 2022 10:00 AM - 11:20 AM Room D (Room D)

座長:唐木田 亮(産業技術総合研究所)[現地]

10:00 AM - 10:20 AM

[1D1-GS-2-01] An Efficient Learning Framework of Sequential Variational Auto-Encoders by Sequential Filtering

〇Tsuyoshi Ishizone1, Tomoyuki Higuchi2, Kazuyuki Nakamura1 (1. Meiji University, 2. Chuo University)

Keywords:deep generative model, time-series prediction, variational inference, sequential Bayesian filtering

Deep sequential generative models have been used in various tasks such as time-series prediction, unseen sequence generation, and time-series anomaly detection. In this report, we focus on models so-called sequential variational auto-encoders and propose an efficient learning framework by sequential Bayes filtering. Although similar prior works provide tighter ELBOs which are lower bounds of the log marginal likelihood, several problems such as the low spread of particles in latent space remain. The proposed framework overcomes these problems by emphasizing practical use and outperforms the prior works for several datasets in predictive ability.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password