Tomoumi Takase

Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias

Ryo Karakida, Kazuki Osawa, Tomoumi Takase, 2022, ArXiv.

Self-paced Data Augmentation for Training Neural Networks pdf

Ryo Karakida, Tomoumi Takase, Hideki Asoh, 2020, Neurocomputing.

Dynamic batch size tuning based on stopping criterion for neural network training

Tomoumi Takase, Tomoumi Takase, 2020, Neurocomputing.

Effective neural network training with adaptive learning rate based on training loss

Satoshi Oyama, Masahito Kurihara, Tomoumi Takase, 2018, Neural Networks.

Why Does Large Batch Training Result in Poor Generalization? A Comprehensive Explanation and a Better Strategy from the Viewpoint of Stochastic Optimization

Satoshi Oyama, Masahito Kurihara, Tomoumi Takase, 2018, Neural Computation.

Difficulty-weighted learning: A novel curriculum-like approach based on difficult examples for neural network training

Tomoumi Takase, Tomoumi Takase, 2019, Expert Syst. Appl..

Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias

Ryo Karakida, Kazuki Osawa, Tomoumi Takase, 2022, ICML.

Evaluation of Stratified Validation in Neural Network Training with Imbalanced Data

Satoshi Oyama, Masahito Kurihara, Tomoumi Takase, 2019, 2019 IEEE International Conference on Big Data and Smart Computing (BigComp).

Longer Distance Weight Prediction for Faster Training of Neural Networks

Satoshi Oyama, Masahito Kurihara, Tomoumi Takase, 2018, 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC).