Pascal Notin
Pascal Notin
Research
Talks
Large scale training; Dropout; CNN; Transformer
Improving Compute Efficacy Frontiers with SliceOut
We introduce a dropout-inspired scheme to train large neural networks faster with no loss in accuracy.
Pascal Notin
,
Aidan N. Gomez
,
Joanna Yoo
,
Yarin Gal
PDF
Cite
arXiv
Press (The Batch)
Cite
×