NeurIPS 2020

Neural Networks Fail to Learn Periodic Functions and How to Fix It


Meta Review

I think this is an interesting submission, that lead to a detailed discussion among the reviewers. Overall the work is novel and looks at an interesting question regarding extrapolation (and dealing with periodic functions). Overall I agree with some of the reviewers that the motivation and generally the write-up of the work could be improved, but I think there is already value in the work. I would like to highlight a few points that are worth considering: * a further discussion regarding how the proposed approach compares to RNNs or autoregressive models when it comes to modeling periodicity * there are some concerns regarding the methodology used (e.g. stopping criterion used) that would be nice to be better clarified in the final version of the work In general, please try to incorporate as much as you can from the clarifications in the rebuttal, and try to answer as many of the worries brought up by the reviewers in order for the paper to have the impact it deserves.