free-spaced-repetition-scheduler
ebisu
free-spaced-repetition-scheduler | ebisu | |
---|---|---|
11 | 4 | |
260 | 303 | |
5.8% | - | |
5.3 | 0.0 | |
24 days ago | 3 months ago | |
Python | Python | |
MIT License | The Unlicense |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
free-spaced-repetition-scheduler
-
Anki – Powerful, intelligent flash cards
... 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.
-
FSRS: A modern, efficient spaced repetition algorithm
Libraries: https://github.com/open-spaced-repetition/free-spaced-repeti...
All are MIT licensed I believe, Anki is primarily AGPL
- The FSRS (Free Spaced Repetition Scheduler) Algorithm
-
FSRS explained, part 1: What it is and how it works
Just read the wiki ¯\_(ツ)_/¯
-
FSRS is supported in AnkiMobile now!
The model used by FSRS: https://github.com/open-spaced-repetition/fsrs4anki/wiki/Free-Spaced-Repetition-Scheduler
- How to use the next-generation spaced repetition algorithm FSRS on Anki?
-
How did I publish a paper in ACMKDD as an undergraduate? A fantastic research experience on spaced repetition algorithm. Open source the code and dataset.
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.
-
New progress in implementing the custom algorithm.
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.
-
Implement a new spaced repetition algorithm based on anki custom scheduling.
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?
ebisu
-
Anki – Powerful, intelligent flash cards
I really wish something like https://github.com/fasiha/ebisu becomes the norm. That is, the idea of fitting the cards to your time (by prioritising) rather than you having to do everything there software wants.
The only bit missing is some algorithm deciding how often to introduce new cards based on your historical data.
-
FSRS: A modern, efficient spaced repetition algorithm
It seems from the description that FSRS still puts an exact review date on each card? This feature was pretty much the reason why I stopped using Anki. I'm not in college and not doing exams, I just want to practice when I feel like it, maybe with large breaks between sessions, and not feel like there's a backlog building up.
I think Anki is a great app, I just wish there was an algorithm that would just randomly sample cards (with probability proportional to how urgently you need to review it) rather than put a review date on them. Something like https://github.com/fasiha/ebisu but available as an Anki plugin (if that supports custom algorithms on mobile yet?) or a similar app with an open format for cards.
-
Study Sets: The reason why cards repeat a lot (algorithm explanation)
"GoodNotes uses the Ebisu algorithm for its spaced repetition feature. Ebisu uses a Bayesian model to estimate the probability of remembering a given flashcard, which allows faster adaptation to changes in recall ability. Both algorithms have been shown to be effective in practice, you can learn more about Ebisu at https://fasiha.github.io/ebisu/ "
-
Am I using Anki wrong?
This is a fundamental issue with SM-2 and how ease factors work. I personally have my Anki settings set up such that there is no ease factor penalty, though I will be working on porting Ebisu v3 to Anki's v3 scheduler once it's ready, which should finally allow us to have proper adaptive ease factors for cards (on all platforms) without the ease hell problem.
What are some alternatives?
fsrs4anki - A modern Anki custom scheduling based on Free Spaced Repetition Scheduler algorithm
ent.hpp - A header-only library that applies various tests to sequences of bytes stored in files and reports the results of those tests. The class is useful for evaluating pseudorandom number generators for encryption and statistical sampling applications, compression algorithms, and other applications where the information density of a file is of interest.
highlight-search-results - Highlight Search Results in the Browser add-on for Anki
dekki - An ML based spaced repetition algorithm to help you learn faster and remember longer.
fsrs4anki-helper - An Anki add-on that reschedules all cards via FSRS4Anki scheduler
option-pricer - Option pricing using Black-Scholes model, Bachelier model, Binomial Trees and Monte Carlo simulation under different stochastic processes
autoEaseFactor - Adjust ease factors in Anki based off of performance in order to hit a target success rate.
Midnight - Midnight Score Probabilities using a Monte Carlo Simulation
SSP-MMC - A Stochastic Shortest Path Algorithm for Optimizing Spaced Repetition Scheduling
monaco - Quantify uncertainty and sensitivities in your computer models with an industry-grade Monte Carlo library.
tatoeba-to-anki - Creates Anki Flash cards from Tatoeba sentences, ordering them by difficulty and downloading audio
LearningCards - Simple collaborative online version of learning/flash cards