Continual learning in recurrent neural networks

By Benjamin Ehret, Christian Henning, Maria R. Cervera, Alexander Meulemans, Johannes von Oswald, Benjamin F. Grewe. 2020

52 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Liyuan Wang
2. Jorge Armando Mendez Mendez
3. Xingxing Zhang
4. Gyuhak Kim
5. Jun Zhu
6. Christian Henning
7. Eric Eaton
8. Johannes von Oswald

Citations in the corpus

• Memory Replay with Data Compression for Continual Learning (2022, positive): “…performance in class-incremental learning (Liu et al., 2021a; Hu et al., 2021) and in numerous other continual learning scenarios, such as audio tasks (Ehret et al., 2020), few-shot (Tao et al., 2020b), semi-supervised (Wang et al., 2021a), and unsupervised continual learning (Khare et al., 2021).”
• Posterior Meta-Replay for Continual Learning (2021, methodology): “(2020) and Ehret et al. (2021). For all experiments other than the lowdimensional toy problems, we apply the chunking strategy to the TC and WG networks.”
• How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition (2022, background): “A separate work evaluated existing lifelong learning methods on recurrent neural networks, finding that they perform reasonably well and are a solid starting point for developing lifelong methods specific to recurrent architectures (Ehret et al., 2021).”