1 code implementation • 28 Jun 2023 • Akifumi Okuno, Yuya Morishita, Yoh-ichi Mototake
This study delves into the domain of dynamical systems, specifically the forecasting of dynamical time series defined through an evolution function.
no code implementations • 13 Apr 2023 • Yoh-ichi Mototake, Y-h. Taguchi
We propose that the correlation length of a dynamical system and the number of samples are crucial for the practical definition of noise variables among the signal variables generated by such a system.
no code implementations • 31 Dec 2019 • Yoh-ichi Mototake
We propose a novel framework that can infer the hidden conservation laws of a complex system from deep neural networks (DNNs) that have been trained with physical data of the system.
no code implementations • NeurIPS 2019 • Kenji Fukumizu, Shoichiro Yamaguchi, Yoh-ichi Mototake, Mirai Tanaka
We theoretically study the landscape of the training error for neural networks in overparameterized cases.
no code implementations • 11 Dec 2018 • Kenji Nagata, Yoh-ichi Mototake, Rei Muraoka, Takehiko Sasaki, Masato Okada
Since the measurement time is strongly related to the signal-to-noise ratio for the Poisson noise model, Bayesian measurement with Poisson noise model enables us to clarify the relationship between the measurement time and the limit of estimation.