Follow
Sho Sonoda
Sho Sonoda
D.Eng., RIKEN AIP
Verified email at toki.waseda.jp - Homepage
Title
Cited by
Cited by
Year
Neural network with unbounded activation functions is universal approximator
S Sonoda, N Murata
Applied and Computational Harmonic Analysis 43 (2), 233-268, 2015
2602015
Double Continuum Limit of Deep Neural Networks
S Sonoda, N Murata
ICML 2017 Workshop on Principled Approaches to Deep Learning, 1-5, 2017
372017
Transport Analysis of Infinitely Deep Neural Network
S Sonoda, N Murata
Journal of Machine Learning Research, 2016
37*2016
A statistical model for predicting the liquid steel temperature in ladle and tundish by bootstrap filter
S Sonoda, N Murata, H Hino, H Kitada, M Kano
ISIJ international 52 (6), 1086-1091, 2012
252012
Neural network with unbounded activations is universal approximator
S Sonoda, N Murata
CoRR, abs/1505.03654, 2015
142015
Sampling hidden parameters from oracle distribution
S Sonoda, N Murata
International Conference on Artificial Neural Networks, 539-546, 2014
122014
Differentiable multiple shooting layers
S Massaroli, M Poli, S Sonoda, T Suzuki, J Park, A Yamashita, H Asama
Advances in Neural Information Processing Systems 34, 16532-16544, 2021
62021
The global optimum of shallow neural network is attained by ridgelet transform
S Sonoda, I Ishikawa, M Ikeda, K Hagihara, Y Sawano, T Matsubara, ...
arXiv preprint arXiv:1805.07517v3, 2019
62019
Learning with optimized random features: Exponential speedup by quantum machine learning without sparsity and low-rank assumptions
H Yamasaki, S Subramanian, S Sonoda, M Koashi
Advances in Neural Information Processing Systems 33, 13674-13687, 2020
52020
Transportation analysis of denoising autoencoders: a novel method for analyzing deep neural networks
S Sonoda, N Murata
NIPS Workshop on Optimal Transport & Machine Learning, 2017
52017
Nonparametric weight initialization of neural networks via integral representation
S Sonoda, N Murata
arXiv preprint arXiv:1312.6461, 2013
52013
EEG dipole source localization with information criteria for multiple particle filters
S Sonoda, K Nakamura, Y Kaneda, H Hino, S Akaho, N Murata, ...
Neural networks 108, 68-82, 2018
42018
Ridge Regression with Over-Parametrized Two-Layer Networks Converge to Ridgelet Spectrum
S Sonoda, I Ishikawa, M Ikeda
International Conference on Artificial Intelligence and Statistics, 2674-2682, 2021
32021
Fast quantum algorithm for learning with optimized random features
H Yamasaki, S Subramanian, S Sonoda, M Koashi
Advances in Neural Information Processing Systems, 1-10, 2020
32020
Sensitivity analysis for controlling molten steel temperature in tundish
N Murata, S Sonoda, H Hino, H Kitada, M Kano
IFAC Proceedings Volumes 45 (23), 270-271, 2012
32012
On the approximation lower bound for neural nets with random weights
S Sonoda, M Li, F Cao, C Huang, YG Wang
arXiv preprint arXiv:2008.08427, 2020
22020
Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis
S Sonoda, I Ishikawa, M Ikeda
arXiv preprint arXiv:2203.01631, 2022
12022
Exponential error convergence in data classification with optimized random features: Acceleration by quantum machine learning
H Yamasaki, S Sonoda
arXiv preprint arXiv:2106.09028, 2021
12021
Fast Approximation and Estimation Bounds of Kernel Quadrature for Infinitely Wide Models
S Sonoda
arXiv preprint arXiv:1902.00648, 2019
12019
深層ニューラルネットの積分表現理論
園田翔
博士論文, 早稲田大学, 2016
12016
The system can't perform the operation now. Try again later.
Articles 1–20