4 papers
Improving Generalization by Permutation Routing Across Model Copies
Shuhei Kashiwamura, Timothee Leleu
We introduce a use of the \(M\)-cover (or \(M\)-layer) transform for machine learning. The method replicates a model \(M\) times, but instead of coupling the copies through paramet…
Uncertainty-Aware Sparse Identification of Dynamical Systems via Bayesian Model Averaging
Shuhei Kashiwamura, Yusuke Kato, Hiroshi Kori +1
In many problems of data-driven modeling for dynamical systems, the governing equations are not known a priori and must be selected phenomenologically from a large set of candidate…
High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator
Yuma Ichikawa, Shuhei Kashiwamura, Ayaka Sakata
Quantized neural network training optimizes a discrete, non-differentiable objective. The straight-through estimator (STE) enables backpropagation through surrogate gradients and i…
Bayesian estimation of coupling strength and heterogeneity in a coupled oscillator model from macroscopic quantities
Yusuke Kato, Shuhei Kashiwamura, Emiri Watanabe +2
Various macroscopic oscillations, such as the heartbeat and the flashing of fireflies, are created by synchronizing oscillatory units (oscillators). To elucidate the mechanism of s…