2020年5月24日
ON LARGE BATCH TRAINING FOR DEEP LEARNING: GENERALIZATION GAP AND SHARP MINIMA
摘要： [TOC] "Keskar N S, Mudigere D, Nocedal J, et al. On Large Batch Training for Deep Learning: Generalization Gap and Sharp Minima[J]. arXiv: Learning, 2 阅读全文
posted @ 2020-05-24 20:24 馒头and花卷 阅读(327) 评论(0) 推荐(0) 编辑