Does the quality of calibration of a model improve with the training data size or even the number of classes?
up vote
0
down vote
favorite
Reliability scores in classification models are really important, and calibration variants such as temperature scaling are one step to improve them, although not perfectly.
Would the calibration of the model improve after using temp-scaling if more training data is introduced? This would seem to be the case if this data would improve the accuracy. But would this still be the case if the accuracy is untouched?
And would the calibration of the model improve after using temp-scaling if more classes are in the network? Of course, each class having the same number of training samples.
classification softmax calibration reliability
asked Nov 22 at 15:55
user3337758
277
add a comment |
up vote
0
down vote
favorite
Reliability scores in classification models are really important, and calibration variants such as temperature scaling are one step to improve them, although not perfectly.
Would the calibration of the model improve after using temp-scaling if more training data is introduced? This would seem to be the case if this data would improve the accuracy. But would this still be the case if the accuracy is untouched?
And would the calibration of the model improve after using temp-scaling if more classes are in the network? Of course, each class having the same number of training samples.
classification softmax calibration reliability
asked Nov 22 at 15:55
user3337758
277
add a comment |
up vote
0
down vote
favorite
up vote
0
down vote
favorite
Reliability scores in classification models are really important, and calibration variants such as temperature scaling are one step to improve them, although not perfectly.
Would the calibration of the model improve after using temp-scaling if more training data is introduced? This would seem to be the case if this data would improve the accuracy. But would this still be the case if the accuracy is untouched?
And would the calibration of the model improve after using temp-scaling if more classes are in the network? Of course, each class having the same number of training samples.
classification softmax calibration reliability
asked Nov 22 at 15:55
user3337758
277
Reliability scores in classification models are really important, and calibration variants such as temperature scaling are one step to improve them, although not perfectly.
Would the calibration of the model improve after using temp-scaling if more training data is introduced? This would seem to be the case if this data would improve the accuracy. But would this still be the case if the accuracy is untouched?
And would the calibration of the model improve after using temp-scaling if more classes are in the network? Of course, each class having the same number of training samples.
classification softmax calibration reliability
classification softmax calibration reliability
asked Nov 22 at 15:55
user3337758
277
asked Nov 22 at 15:55
user3337758
277
asked Nov 22 at 15:55
user3337758
277
asked Nov 22 at 15:55
user3337758
277
asked Nov 22 at 15:55
user3337758
277
277
add a comment |
add a comment |
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53434548%2fdoes-the-quality-of-calibration-of-a-model-improve-with-the-training-data-size-o%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
