Why Does Large Batch Training Result in Poor Generalization? A Comprehensive Explanation and a Better Strategy from the Viewpoint of Stochastic Optimization
['Tomoumi Takase', 'Satoshi Oyama', 'Masahito Kurihara']
/
Neural Computation
/ Vol. 30
/ No. 7
まだレビューは投稿されていません。あなたが最初のレビューを書きませんか？