activity
20212026
most citedLearning where to learn: Gradient sparsity in meta and continual learning

24 citations · 87 across the 13 of their papers we have counts for

collaborators
Showing 2024Show all

1 paper · 1 filter

cs.LG2024★ 12 cited

Recurrent neural networks: vanishing and exploding gradients are not the end of the story

Nicolas Zucchet, Antonio Orvieto

Recurrent neural networks (RNNs) notoriously struggle to learn long-term memories, primarily due to vanishing and exploding gradients. The recent success of state-space models (SSM…