no code implementations • 27 Mar 2024 • Tomoya Nishikata, Jun Ohkubo
The Koopman operator is one of them, which enables us to employ linear analysis for nonlinear dynamical systems.
no code implementations • 18 Feb 2024 • Naoki Sugishita, Kayo Kinjo, Jun Ohkubo
Nonlinearity plays a crucial role in deep neural networks.
no code implementations • 27 Dec 2023 • Felix Köster, Kazutaka Kanno, Jun Ohkubo, Atsushi Uchida
Photonic reservoir computing has been recently utilized in time series forecasting as the need for hardware implementations to accelerate these predictions has increased.
no code implementations • 5 Dec 2023 • Yoshiki Sato, Makiko Konoshima, Hirotaka Tamura, Jun Ohkubo
Ising formulations are widely utilized to solve combinatorial optimization problems, and a variety of quantum or semiconductor-based hardware has recently been made available.
no code implementations • 8 Jun 2023 • Naoki Sugishita, Jun Ohkubo
We propose a new approach to constructing a neural network for predicting expectations of stochastic differential equations.
no code implementations • 18 Jan 2023 • Yuki Furue, Makiko Konoshima, Hirotaka Tamura, Jun Ohkubo
However, there is a severe constraint on the number of binary variables with such machines.
no code implementations • 21 Feb 2021 • Kotaro Furuya, Jun Ohkubo
It is possible to implement the proposed learning method for event-driven systems.
no code implementations • 10 Dec 2020 • Jun Ohkubo
This paper gives a new insight into nonlinear stochastic optimal control problems from the perspective of Koopman operators.
Optimization and Control Statistical Mechanics
no code implementations • 11 Jan 2020 • Tomohiro Yokota, Makiko Konoshima, Hirotaka Tamura, Jun Ohkubo
We propose a quadratic unconstrained binary optimization (QUBO) formulation of the l1-norm, which enables us to perform sparse estimation of Ising-type annealing methods such as quantum annealing.