Multi-step time series generator for molecular dynamics

Katsuhiro Endo, Katsufumi Tomobe, Kenji Yasuoka

研究成果: Conference contribution

9 被引用数 (Scopus)

抄録

Molecular dynamics (MD) is a powerful computational method for simulating molecular behavior. Deep neural networks provide a novel method of generating MD data efficiently, but there is no architecture that mitigates the well-known exposure bias accumulated by multi-step generations. In this paper, we propose a multi-step time series generator using a deep neural network based on Wasserstein generative adversarial nets. Instead of sparse real data, our model evolves a latent variable z that is densely distributed in a low-dimensional space. This novel framework successfully mitigates the exposure bias. Moreover, our model can evolve part of the system (Feature extraction) with any time step (Step skip), which accelerates the efficient generation of MD data. The applicability of this model is evaluated through three different systems: harmonic oscillator, bulk water, and polymer melts. The experimental results demonstrate that our model can generate time series of the MD data with sufficient accuracy to calculate the physical and important dynamical statistics.

本文言語English
ホスト出版物のタイトル32nd AAAI Conference on Artificial Intelligence, AAAI 2018
出版社AAAI press
ページ2192-2199
ページ数8
ISBN(電子版)9781577358008
出版ステータスPublished - 2018
イベント32nd AAAI Conference on Artificial Intelligence, AAAI 2018 - New Orleans, United States
継続期間: 2018 2月 22018 2月 7

出版物シリーズ

名前32nd AAAI Conference on Artificial Intelligence, AAAI 2018

Other

Other32nd AAAI Conference on Artificial Intelligence, AAAI 2018
国/地域United States
CityNew Orleans
Period18/2/218/2/7

ASJC Scopus subject areas

  • 人工知能

フィンガープリント

「Multi-step time series generator for molecular dynamics」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル