NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:1052
Title:Meta-Learning Representations for Continual Learning

Two of the reviewers increased their score after reading the rebuttal. All three reviewers now provide accepting scores. The reviewers particularly appreciated the authors response. In particular the additional experiment on mini-imagenet as it re-confirms the original idea and gives consistent results as those obtained with simpler datasets. The idea of borrowing meta-learning ideas to tackle the continual learning problem is interesting and the empirical results sufficient. The AC encourages the authors to include clarifications of the experimental protocol in the final manuscript and the discussion of why the performance of EWC is that low (as done in their response).