Directory of Researchers

Inoue Hiroaki
Graduate School of Engineering / Department of Electrical and Electronic Engineering
Assistant Professor
Electro-Communication Engineering
Last Updated :2022/10/04

Researcher Profile and Settings

Affiliation

  • <Faculty / Graduate School / Others>

    Graduate School of Engineering / Department of Electrical and Electronic Engineering
  • <Related Faculty / Graduate School / Others>

    Faculty of Engineering / Department of Electrical and Electronic Engineering, Center for Mathematical and Data Sciences

Teaching

Research Activities

Research Interests

  • 知的学習論
  • データ駆動化学
  • データ同化
  • 動的システム推定
  • 確率的時系列解析
  • ベイズ統計
  • 計算脳科学
  • イメージングデータ

Research Areas

  • Informatics / Soft computing
  • Informatics / Intelligent informatics

Awards

  • Jun. 2022 一般社団法人日本応用数理学会, 2021年度若手優秀講演賞, データ駆動型アプローチによる神経ネットワークのダイナミクス推定

  • Mar. 2017 Excellent Oral Presentation Award, 1st International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence

Published Papers

  • Hiroaki Inoue, Koji Hukushima, Toshiaki Omori

    Extracting latent nonlinear dynamics from observed time-series data is important for understanding a dynamic system against the background of the observed data. A state space model is a probabilistic graphical model for time-series data, which describes the probabilistic dependence between latent variables at subsequent times and between latent variables and observations. Since, in many situations, the values of the parameters in the state space model are unknown, estimating the parameters from observations is an important task. The particle marginal Metropolis–Hastings (PMMH) method is a method for estimating the marginal posterior distribution of parameters obtained by marginalization over the distribution of latent variables in the state space model. Although, in principle, we can estimate the marginal posterior distribution of parameters by iterating this method infinitely, the estimated result depends on the initial values for a finite number of times in practice. In this paper, we propose a replica exchange particle marginal Metropolis–Hastings (REPMMH) method as a method to improve this problem by combining the PMMH method with the replica exchange method. By using the proposed method, we simultaneously realize a global search at a high temperature and a local fine search at a low temperature. We evaluate the proposed method using simulated data obtained from the Izhikevich neuron model and Lévy-driven stochastic volatility model, and we show that the proposed REPMMH method improves the problem of the initial value dependence in the PMMH method, and realizes efficient sampling of parameters in the state space models compared with existing methods.

    Lead, MDPI AG, 12 Jan. 2022, Entropy, 24 (1), 115:1 - 20, English

    [Refereed]

    Scientific journal

  • Data-Driven Method for Estimating Neuronal Nonlinear Dynamics from Noisy Partial Observation

    Hiroaki Inoue, Toshiaki Omori

    Lead, Jan. 2022, Proceedings of the 27th International Symposium on Artificial Life and Robotics, English

    [Refereed]

  • Hiroaki Inoue, Koji Hukushima, Toshiaki Omori

    Lead, Physical Society of Japan, 15 Oct. 2021, Journal of the Physical Society of Japan, 90 (10), 104801:1 - 9, English

    [Refereed]

    Scientific journal

  • Hiroaki Inoue, Koji Hukushima, Toshiaki Omori

    Lead, Physical Society of Japan, 15 Oct. 2020, Journal of the Physical Society of Japan, 89 (10), 104801:1 - 7, English

    [Refereed]

    Scientific journal

  • Hiroaki Inoue, Toshiaki Omori

    Lead, ACM Press, 25 Mar. 2017, ACM International Conference Proceeding Series, English

    [Refereed]

    International conference proceedings

  • Statistical Estimation of Neural System Using Calcium Imaging

    Hiroaki Inoue, Toshiaki Omori

    Lead, Nov. 2015, Proceedings of 16th International Symposium on Advanced Intelligent Systems, English

    [Refereed]

Presentations

  • Extracting nonlinear latent dynamics of neurons using replica exchange particle Markov chain Monte Carlo method

    Hiroaki Inoue, Toshiaki Omori

    The 10th RIEC International Symposium on Brain Functions and Brain Computer, 19 Feb. 2022, English

  • Data-Driven Method for Estimating Neuronal Nonlinear Dynamics from Noisy Partial Observation

    Hiroaki Inoue, Toshiaki Omori

    The 27th International Symposium on Artificial Life and Robotics, 27 Jan. 2022, English

  • 粒子マルコフ連鎖モンテカルロ法による時系列データの潜在ダイナミクス推定

    井上広明

    DuEX若手研究者交流会, 07 Jan. 2022, Japanese

  • データ駆動型アプローチによる神経ネットワークのダイナミクス推定

    井上 広明, 大森 敏明

    日本応用数理学会 2021年度年会, 08 Sep. 2021, Japanese

  • Estimation of neural dynamics with particle Markov chain Monte Carlo

    Hiroaki Inoue, Koji Hukishima, Toshiaki Omori

    The 9th RIEC International Symposiumon Brain Functions and Brain Computer, 05 Dec. 2020, English

  • データ駆動型アプローチに基づく神経活動の解析

    井上広明, 大森敏明

    第4回 極みプロジェクトシンポジウム, 03 Sep. 2020, Japanese

  • 粒子マルコフ連鎖モンテカルロ法を用いた神経ネットワークの構造推定

    井上広明, 大森敏明

    第2 回極みプロジェクトシンポジウム/第6 回イメージング数理研究会, 02 Sep. 2019, Japanese

  • データ駆動型アプローチに基づく神経システムの数理モデル推定

    政廣蓮, 山崎潤也, 大塚慎也, 井上広明, 大森敏明

    第5回イメージング数理研究会, 2018, Japanese

  • Bayesian Estimation of Neural Systems using Particle-Gibbs

    Hiroaki Inoue, Toshiaki Omori

    International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence, 26 Mar. 2017, English

  • Particle-MCMC による神経ネットワークの推定

    井上広明, 大森敏明

    定量生物学の会第八回年会, Jan. 2017, Japanese

  • Estimation of Neural System Using Particle MCMC

    井上広明, 大森敏明

    第60回システム制御情報学会研究発表講演会 (SCI'16), 26 May 2016, Japanese

  • Bayesian Probabilistic Approach for Estimating Neural System Based on Calcium Imaging

    Hiroaki Inoue, Toshiaki Omori

    Cyber-Physical System for Smarter World (CPS-SW 2016), 24 Mar. 2016, English

  • Statistical Estimation of Neural System Using Calcium Imaging

    Hiroaki Inoue, Toshiaki Omori

    the 16th International Symposium on Advanced Intelligent Systems (ISIS2015), 06 Nov. 2015, Japanese

  • Statistical Estimation of Neural System Using Calcium Imaging

    井上広明, 大森敏明

    第59回システム制御情報学会研究発表講演会 (SCI'15), 20 May 2015, Japanese

  • Extracting Nonlinear Dynamical Systems Using Replica Exchange Particle Markov Chain Monte Carlo Methods

    Hiroaki Inoue

    First Symposium on Data-driven Modeling in Complex Systems, 30 Mar. 2022

  • Estimation of dynamics of neural systems using replica exchange particle Markov chain Monte Carlo method

    井上広明, 大森敏明

    第66回システム制御情報学会研究発表講演会(SCI'22), 20 May 2022

  • Simultaneous Estimation of Latent Variables and Parameters Using Self-Organizing State Space Model with Temperatures

    Hiroaki Inoue, Toshiaki Omori

    第21回情報科学技術フォーラム, 15 Sep. 2022

  • ベイズ推論に基づく神経ネットワークのシステム同定

    井上広明, 大森敏明

    次世代光散乱イメージング科学研究センターキックオフシンポジウム, 27 Jun. 2022

  • 動的サンプリングを用いた連合学習型勾配ブースティング決定木の継続学習

    三浦啓吾, 井上広明, Kim Sangwook, 王立華, 小澤誠一

    第30回インテリジェント・システム・シンポジウム, 22 Sep. 2022

  • 温度の効果を導入した自己組織化状態空間モデルによる神経ダイナミクスの推定

    井上広明, 大森敏明

    日本応用数理学会 2022年度年会, 08 Sep. 2022

Association Memberships

  • システム制御情報学会

    Apr. 2022 - Present
  • 人工知能学会

    Sep. 2021 - Present
  • 情報処理学会

    May 2022 - Present

Research Projects

  • 多次元時系列データに潜在する動的な因果構造のデータ駆動型推論アルゴリズムの構築

    井上 広明

    Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research Grant-in-Aid for Early-Career Scientists, Grant-in-Aid for Early-Career Scientists, Kobe University, Apr. 2022 - Mar. 2025