Neural Process (NP) [8] is a class of stochastic processes defined by parametric neural networks.

Theoretically, we prove a novel bound on the errors introduced by LSH-SMILE.

To address these issues, we propose a self-supervised intrinsic rewardELIGN expectation alignment - inspired by the self-organization principle in Zoology.

Recent efforts on learning cross-domain invariant representations using deep networks generally fall into twocategories.