22 citations · 148 across the 31 of their papers we have counts for
17 papers · 1 filter
Effective Method for Inverse Ising Problem under Missing Observations in Restricted Boltzmann Machines
Kaiji Sekimoto, Muneki Yasuda
Restricted Boltzmann machines (RBMs) are energy-based models analogous to the Ising model and are widely applied in statistical machine learning. The standard inverse Ising problem…
Free Energy Evaluation Using Marginalized Annealed Importance Sampling
Muneki Yasuda, Chako Takahashi
The evaluation of the free energy of a stochastic model is considered a significant issue in various fields of physics and machine learning. However, the exact free energy evaluati…
Spatial Monte Carlo Integration with Annealed Importance Sampling
Muneki Yasuda, Kaiji Sekimoto
Evaluating expectations on an Ising model (or Boltzmann machine) is essential for various applications, including statistical machine learning. However, in general, the evaluation…
A Generalization of Spatial Monte Carlo Integration
Muneki Yasuda, Kei Uchizawa
Spatial Monte Carlo integration (SMCI) is an extension of standard Monte Carlo integration and can approximate expectations on Markov random fields with high accuracy. SMCI was app…
Consistent Batch Normalization for Weighted Loss in Imbalanced-Data Environment
Muneki Yasuda, Yeo Xian En, Seishirou Ueno
In this study, classification problems based on feedforward neural networks in a data-imbalanced environment are considered. Learning from an imbalanced dataset is one of the most…
Improvement of Batch Normalization in Imbalanced Data
Muneki Yasuda, Seishirou Ueno
In this study, we consider classification problems based on neural networks in data-imbalanced environment. Learning from an imbalanced data set is one of the most important and pr…