Networks routinely forget some test points during training even while overall accuracy improves, and combining mid-training checkpoints selected by a forget-score recovers some of this lost accuracy.
S.; Maharaj, T.; Fischer, A.; Courville, A.; Bengio, Y.; et al
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On Local Overfitting and Forgetting in Deep Neural Networks
Networks routinely forget some test points during training even while overall accuracy improves, and combining mid-training checkpoints selected by a forget-score recovers some of this lost accuracy.