Comments (9)
Bad case 1: very low initial stability
Solution: decrease the lower limit of w[0], w[1], w[2] and w[3] from 0.1 to 0.01.
from srs-benchmark.
Bad case 2: very long elapsed days for first reviews
Solution: filter out reviews with delta_t > 100.
from srs-benchmark.
Bad case 3: non-monotonous initial stability
The user's initial stability of good
is lower than the initial stability of hard
. And the data is enough.
Solution: don't compare initial stability with each other when the number of reviews is enough.
from srs-benchmark.
So do you think we should allow S0 to be non-monotonous? I think we shouldn't - users will be confused if, for example, their Easy interval is shorter than their Good interval.
from srs-benchmark.
It doesn't affect most users. And it could improve the accuracy of affected users significantly.
from srs-benchmark.
I think the confusion outweighs any accuracy benefits. @user1823, what do you think?
from srs-benchmark.
Solution: don't compare initial stability with each other when the number of reviews is enough.
Just like Expertium, I don't think that it is a good idea because interval for Good
being less than Hard
(or any other pair) would not be acceptable.
I think that in this case, the user has two (or more) different types of cards. So, more accurate parameters can be obtained if the user generates different parameters for different types of cards.
from srs-benchmark.
Solution: filter out reviews with delta_t > 100.
I agree that this makes sense for Again, Hard and Good, but probably not for Easy. For Easy, the limit should be higher. Perhaps 365 days?
from srs-benchmark.
OK. I reverted the solution of bad case 3 and relaxed the filter for bad case 1.
from srs-benchmark.
Related Issues (20)
- Inclusion of any of the boosting models HOT 23
- Remove collecitons of people who misuse Hard from the calculation of the default parameters HOT 4
- visualize metrics over time HOT 2
- [Feature Request] Train a gradient-boosted decision tree HOT 36
- Some weird first forgetting curves HOT 11
- [Feature request] Add confidence intervals for all metrics HOT 9
- accidental post
- Revlogs parsing HOT 12
- [Question] A βrawβ version of the tiny_dataset.zip HOT 3
- [Feature Request] Add a BiLSTM HOT 2
- [Feature request] Add the ACT-R model (see paper) HOT 21
- [TODO] Add DASH and its variants HOT 13
- [Feature request] A quantitative measure of cheating HOT 9
- Write an article about binned RMSE and cheating calibration metrics HOT 7
- Ebisu? HOT 7
- [Question] Some more details from a ML perspective HOT 8
- Cannot download dataset from huggingface HOT 4
- Neural network scheduler HOT 42
- Add MCC
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from srs-benchmark.