← Search

Maria Cervera

2 accepted papers

2021

Continual learning in recurrent neural networks

ICLR 2021poster

While a diverse collection of continual learning (CL) methods has been proposed to prevent catastrophic forgetting, a thorough investigation of their effectiveness for processing sequential data with recurrent neural networks (RNNs) is lacking. Here, we provide the first comprehensive evaluation of…

2021

Posterior Meta-Replay for Continual Learning

NeurIPS 2021poster

Learning a sequence of tasks without access to i.i.d. observations is a widely studied form of continual learning (CL) that remains challenging. In principle, Bayesian learning directly applies to this setting, since recursive and one-off Bayesian updates yield the same result. In practice, however,…