most citedUnsupervised Replay Strategies for Continual Learning with Limited Data

1 citations · 1 across the 7 of their papers we have counts for

collaborators
Showing cs.NEShow all

1 paper · 1 filter

cs.NE2024

Sleep-Like Unsupervised Replay Improves Performance when Data are Limited or Unbalanced

Anthony Bazhenov, Pahan Dewasurendra, Giri Krishnan +1

The performance of artificial neural networks (ANNs) degrades when training data are limited or imbalanced. In contrast, the human brain can learn quickly from just a few examples.…