Comments (4)
It can be useful for some users but it can be detrimental for others (especially those who are using Anki for more than 5-10 years).
perhaps there is already something similar.
No, there isn't.
from fsrs-optimizer.
Fair point. Then how about this:
leech_threshold = max(10, percentile(leeches, 0.95))
reps_threshold = max(40, percentile(reps, 0.95))
This is more adaptive. For users with young collections, the thresholds will be 10 and 40. For users with old collections, thresholds will be higher. Both the number of leeches and the number of reviews need to exceed the threshold in order for that card to be excluded from optimization.
from fsrs-optimizer.
@user1823 @L-M-Sherlock maybe we should also remove "anti-leeches" - cards with no Again ratings. For example, remove cards with n(Again)=0 and n(reviews)>10. Just like leeches, they do not follow the usual memory patterns, just in a different way.
EDIT: actually no, that wouldn't work. Assuming 90% probability of recall (for example), there is a 0.9^10=0.349 chance that a user would get a card right 10 times in a row. So we would remove way too many cards. The number of reviews needed to identify "anti-leeches" would be way too high, like 30.
Still, my suggestion about the leech threshold in my previous comment sounds good.
from fsrs-optimizer.
Users can filter out those cards via specific query: https://docs.ankiweb.net/searching.html#card-properties
from fsrs-optimizer.
Related Issues (20)
- Use the median instead of the mean for recall costs and learn cost HOT 8
- how to input data from obsidian-spaced-repetition-recall, ob-revlog.csv, into optimizer HOT 26
- [Feature request] A way to extrapolate values of S0 without curve_fit HOT 8
- [BUG] file not found when running local optimizer for multiple decks HOT 2
- Use results from benchmark experiment as initial values of S0 HOT 12
- Command Line typo on usage section fsrs-optimizer doesn't exist [BUG] HOT 1
- [BUG] Loosen the clamping for w[10] and w[8] HOT 5
- [Feature Request] Loosen the clampings for w[9] HOT 5
- index 1 is out of bounds for axis 0 with size 1 [BUG] HOT 1
- Training data is inadequate. HOT 5
- [Question] Explain how the optimizer calculates retention that minimizes review times HOT 12
- [Feature Request] make the simulator more precise by using different values of recall_cost for Hard, Good and Easy
- [Bug] Can't use absolute path as arg HOT 1
- [BUG] 'Optimizer' object has no attribute 'w' HOT 1
- [Feature request] Improve post-lapse stability analysis HOT 13
- See if this code could be used to speed up finding optimal retention HOT 16
- [Feature Request] Investigate how robust are parameters and RMSE HOT 18
- Optimized w[3] too low HOT 12
- [BUG] Optimizer error: "stack expects each tensor to be equal size, but got [...] at entry 0 and [...] at entry 1" HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fsrs-optimizer.