activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Extraction of linearized models from pre-trained networks via knowledge distillation

Fumito Kimura, Jun Ohkubo

Recent developments in hardware, such as photonic integrated circuits and optical devices, are driving demand for research on constructing machine learning architectures tailored f…

cs.LG2025

Koopman operator-based discussion on partial observation in stochastic systems

Jun Ohkubo

It is sometimes difficult to achieve a complete observation for a full set of observables, and partial observations are necessary. For deterministic systems, the Mori-Zwanzig forma…

cs.LG2025

Integrated utilization of equations and small dataset in the Koopman operator: applications to forward and inverse problems

Ichiro Ohta, Shota Koyanagi, Kayo Kinjo +1

In recent years, there has been a growing interest in data-driven approaches in physics, such as extended dynamic mode decomposition (EDMD). The EDMD algorithm focuses on nonlinear…

cs.LG2024

Aspects of importance sampling in parameter selection for neural networks using ridgelet transform

Hikaru Homma, Jun Ohkubo

The choice of parameters in neural networks is crucial in the performance, and an oracle distribution derived from the ridgelet transform enables us to obtain suitable initial para…

cs.LG2024

Extraction of nonlinearity in neural networks with Koopman operator

Naoki Sugishita, Kayo Kinjo, Jun Ohkubo

Nonlinearity plays a crucial role in deep neural networks. In this paper, we investigate the degree to which the nonlinearity of the neural network is essential. For this purpose,…