mnemosyne VS free-spaced-repetition-scheduler

I wonder if there is plan for this to land in Mnemosyne[1]. I prefer Mnemosyne over Anki because I can self-host the web-sync server.

1: https://mnemosyne-proj.org/

I have tried using spaced repetition with Mnemosyne for math, specifically for learning Category Theory. It did help. Spaced repetition seems to work better for me if the answers to the questions are short (like learning Spanish vocabulary). When doing math, you often want to remember an entire definition, which might be too long to use spaced repetition flash cards effectively.

I've had good luck with spaced repetition using mnemosyne for lots of other stuff but haven't tried it for knots yet

Also, take the time to learn everyone's name and face. I use a flash card program like Mnemosyne to copy people's photos from the corporate directory. Learn them all the first week or even in the first couple of days.

https://mnemosyne-proj.org/ use this, make every relevant term a flash card and event a flash card. It takes forever to populate, but you learn on entry in addition to “study”.

[15] https://mnemosyne-proj.org/ - OS alternative to Anki

Anki is a spaced-repetition system based on Mnemosyne for studying flashcards in such a way that optimally loads facts into and maintains them in long-term memory. During daily study sessions, Anki shows flash cards, and you self-rate your ability to recall each correct answer. You review easier cards on a maintenance schedule, and Anki schedules the ones you have trouble with more frequently.

Some time ago I saw several posts about a machine learning based scheduler for Anki. There is another project known as mnemosyne that conducts research into long term learning. Do you want similar changes to Anki's scheduler?

... https://github.com/open-spaced-repetition/fsrs4anki/wiki/The... ...

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.

Libraries: https://github.com/open-spaced-repetition/free-spaced-repeti...

All are MIT licensed I believe, Anki is primarily AGPL

Just read the wiki ¯\_(ツ)_/¯

The model used by FSRS: https://github.com/open-spaced-repetition/fsrs4anki/wiki/Free-Spaced-Repetition-Scheduler

Also, sorry for nitpicking, but I just checked the code here, and I saw that you changed the formula for post-lapse stability, but you didn't update the formula in the description here.

I have another one, also about difficulty. Look at the long "Stability updating formula after successful review" formula, there is a term D-b. This seems very counter-intuitive. A large value of D corresponds to an easy card, but thanks to that formula it will produce a very small change in stability. A small value of D corresponds to a difficult card, but according to that formula it will change stability a lot.

So I checked this and it seems that there's a whole bunch of different parameters (initial difficulty, initial stability, etc), and a lot of them are constant. So the next step would be to use some kind of optimization algorithm, like gradient descent, to optimize those parameters based on user's review history, right?