pith. sign in

Efficient and effec- tive training of sparse recurrent neural net- works

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Learn&Drop: Fast Learning of CNNs based on Layer Dropping

cs.CV · 2026-04-25 · unverdicted · novelty 5.0

Learn&Drop dynamically drops CNN layers during training based on change and continuation scores to reduce forward-pass FLOPs by up to 83% and halve training time on VGG and ResNet models with little accuracy loss.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learn&Drop: Fast Learning of CNNs based on Layer Dropping cs.CV · 2026-04-25 · unverdicted · none · ref 9

    Learn&Drop dynamically drops CNN layers during training based on change and continuation scores to reduce forward-pass FLOPs by up to 83% and halve training time on VGG and ResNet models with little accuracy loss.