Sho Sonoda

Profile Information

Affiliation: RIKEN

Degree: 博士（工学）(早稲田大学)

ORCID ID: https://orcid.org/0000-0001-7242-4740
J-GLOBAL ID: 201801004612031499
researchmap Member ID: B000291243

External link: https://sites.google.com/view/shosonoda/

Research Interests

Research Areas

Informatics / Intelligent informatics /

Major Papers

Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis

Sho Sonoda, Isao Ishikawa, Masahiro Ikeda

Proceedings of the 39th International Conference on Machine Learning, 162 20405-20422, 2022 Peer-reviewedLead author
Ridge Regression with Over-parametrized Two-Layer Networks Converge to Ridgelet Spectrum.

Sho Sonoda, Isao Ishikawa, Masahiro Ikeda

The 24th International Conference on Artificial Intelligence and Statistics(AISTATS), 2674-2682, 2021 Peer-reviewedLead author
Transport Analysis of Infinitely Deep Neural Network

Sho Sonoda, Noboru Murata

Journal of Machine Learning Research, 20(2) 1-52, 2019 Peer-reviewed
Neural network with unbounded activation functions is universal approximator

Sho Sonoda, Noboru Murata

Applied and Computational Harmonic Analysis, 43(2) 233-268, Sep, 2017 Peer-reviewedLead authorCorresponding author
Integral Representation Theory of Deep Neural Networks

Sho Sonoda

Waseda University, Feb, 2017 Peer-reviewed

Misc.

The global optimum of shallow neural network is attained by ridgelet transform

Sho Sonoda, Isao Ishikawa, Masahiro Ikeda, Kei Hagihara, Yoshihiro Sawano, Takuo Matsubara, Noboru Murata

May 19, 2018
Invited Talk : Transportation aspect of deep neural network

117(210) 185-188, Sep 15, 2017
New Lerning Algorythm of Neural Network using Integral Representation and Kernel Herding

116(500) 25-31, Mar 6, 2017
Transportation aspect of infinitely deep denoising autoencoder

116(300) 297-304, Nov 16, 2016
Toward Ridgelet Analysis of Deep Learning (Wavelet analysis and signal processing)

Sonoda Sho, Murata Noboru

RIMS Kokyuroku, 2001 64-73, Jul, 2016
Sampling Learning Algorithm by Oracle Distribution

SONODA Sho, MURATA Noboru

Technical report of IEICE. PRMU, 114(197) 137-142, Sep 1, 2014
Sampling Learning Algorithm by Oracle Distribution

Sho Sonoda, Noboru Murata

IPSJ SIG Notes. CVIM, 2014(24) 1-6, Aug 25, 2014
Current Dipole Localization from EEG by Multiple Particle Filters and Model Selection

KANEDA Yuki, SONODA Sho, HINO Hideitsu, MURATA Noboru

114(105) 91-96, Jun 25, 2014
Current Dipole Localization from EEG by Multiple Particle Filters and Model Selection

Yuki Kaneda, Sho Sonoda, Hideitsu Hino, Noboru Murata

IPSJ SIG technical reports, 2014(15) 1-6, Jun 18, 2014
ブートストラップフィルタによる溶鋼温度分布の予測と制御

園田翔, 村田昇, 日野英逸, 進藤史裕, 北田宏, 加納学

材料とプロセス(CD-ROM), 24(1) ROMBUNNO.TO9, Mar 1, 2011

Research Projects

複雑データに内在する深層構造の理論と応用

戦略的基礎研究推進事業さきがけ, 科学技術振興機構, Oct, 2021 - Mar, 2025

園田翔
Transportation analysis of deep neural networks

Grants-in-Aid for Scientific Research Grant-in-Aid for Early-Career Scientists, Japan Society for the Promotion of Science, Apr, 2018 - Mar, 2022
積分表現理論によるディープニューラルネットの解析と設計指標の開発

科学研究費助成事業特別研究員奨励費, 日本学術振興会, Apr, 2015 - Mar, 2017

園田翔

Profile Information

Research Interests

Research Areas

Major Papers

Misc.

Research Projects

Menu

Coauthors