I'm not really sure what you mean? It's been empirically validated to predict how you remember better than alternatives (or equal to SM-17) (essentially when it predicts that your % recall is below a certain threshold, it just shows you the card)
Re:Anki – Powerful, intelligent flash cards
by kouteiheika on Sunday January 28, 2024 @12:51PM
(#39168024)
It doesn't matter whether this actually models how memory works in reality, as long as it has actual predictive capabilities which correlate to how it works in practice.
And this can be easily verified with data and simulations. The algorithm predicts how likely it is that you'll remember a given piece of information (e.g. in three days you'll remember this card with 80% probability), so if you can get a big dataset of reviews and run it through the algorithm you can easily check how accurate it is, e.g by calculating a brier score, or by comparing predicted vs actual recall curves.
Source: I've developed an even better algorithm than FSRS (I've directly compared them in the past, although that was quite a while ago so it might have been for one of the older versions of FSRS, so I'm not sure how the newest one compares), and now I'm working on an even better one.
Re:Anki – Powerful, intelligent flash cards
by jarrett-ye on Sunday January 28, 2024 @09:05PM
(#39171965)
It's welcome to compare your algorithm with FSRS. Here is the benchmark of FSRS: https://github.com/open-spaced-repetition/fsrs-benchmark
Re:Anki – Powerful, intelligent flash cards
by kouteiheika on Tuesday January 30, 2024 @08:28PM
(#39198546)
Yes, I'll probably do that once I'm finished with the new version of my algorithm.
I'm not sure I believe we understand our own learning/memory anything like enough for this not to be total pseudoscience? Reminds me of A Beautiful Mind.