ON LARGE BATCH TRAINING FOR DEEP LEARNING: GENERALIZATION GAP AND SHARP MINIMA

文章目錄 概 主要內容 一些解決辦法 Keskar N S, Mudigere D, Nocedal J, et al. On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima[J]. arXiv: Learning, 2016. 作者代碼 @article{keskar2016on, title
相關文章
相關標籤/搜索