NeurIPS 2020

Learning to Learn Variational Semantic Memory

Meta Review

This paper adds uncertainty modelling and an external memory to prototypical networks and achieves good performance gains as a result. The paper is above the bar for acceptance. There were a number of extra details, clarifications, and related work that was brought up in the reviews and rebuttal that should be incorporated into the final camera ready version. The authors should also compare to the DKM model and try to quantify the benefit of uncertainty modelling, as promised in the rebuttal.