Computing gradients through backpropagation is crucial to the success of modern deep neural networks.

In many applications, we desire neural networks to exhibit invariance or equivari-ance to certain groups due to symmetries inherent in the data. Recently, frame-averaging methods emerged to be a unified framework for attaining symmetries efficiently by averaging over input-dependent subsets of the group, i.e., frames. What we currently lack is a principled understanding of the design of frames.

However, none of these models were examined in memory tasks.

On one hand, the knowledge learned from public data is implicitly transferred into the private model.