> Cooke says that returning to a memory is crucial, and the Memrise has algorithms that learn when a student needs a friendly reminder, via an email say, to recall a certain lesson.

Are these algorithms any different than the ones used by Anki et al? I'd be surprised if they were. The novel thing for the isolated case (gamification is interesting but I'm not sure how general that is for helping) seems to be thickly layering on the mnemonic tricks instead of relying on pure flash-card memorization of information, is this correct?