Is it a red flag that increasing the number of parameters makes the model less able to overfit small amounts...
$begingroup$
I'm training a deep network (CNN-LSTM-CRF) for Named Entity Recognition. Is there a reason that increasing the number of parameters would make the network less able to overfit a small training set (~20 sentences), or does this indicate a serious bug in the code?
deep-learning nlp lstm cnn named-entity-recognition
asked Jul 9 '18 at 1:24
SolveItSolveIt
1162
$endgroup$
bumped to the homepage by Community♦ 3 hours ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
add a comment |
$begingroup$
I'm training a deep network (CNN-LSTM-CRF) for Named Entity Recognition. Is there a reason that increasing the number of parameters would make the network less able to overfit a small training set (~20 sentences), or does this indicate a serious bug in the code?
deep-learning nlp lstm cnn named-entity-recognition
asked Jul 9 '18 at 1:24
SolveItSolveIt
1162
$endgroup$
bumped to the homepage by Community♦ 3 hours ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
3
$begingroup$
No, it means you have to train it more.
$endgroup$
– Vaalizaadeh
Jul 9 '18 at 1:36
1
$begingroup$
"less able to overfit" -- explain how it is that you are measuring this, and we can help more.
$endgroup$
– Scott
Jul 9 '18 at 4:11
add a comment |
$begingroup$
I'm training a deep network (CNN-LSTM-CRF) for Named Entity Recognition. Is there a reason that increasing the number of parameters would make the network less able to overfit a small training set (~20 sentences), or does this indicate a serious bug in the code?
deep-learning nlp lstm cnn named-entity-recognition
asked Jul 9 '18 at 1:24
SolveItSolveIt
1162
$endgroup$
I'm training a deep network (CNN-LSTM-CRF) for Named Entity Recognition. Is there a reason that increasing the number of parameters would make the network less able to overfit a small training set (~20 sentences), or does this indicate a serious bug in the code?
deep-learning nlp lstm cnn named-entity-recognition
deep-learning nlp lstm cnn named-entity-recognition
asked Jul 9 '18 at 1:24
SolveItSolveIt
1162
asked Jul 9 '18 at 1:24
SolveItSolveIt
1162
asked Jul 9 '18 at 1:24
SolveItSolveIt
1162
asked Jul 9 '18 at 1:24
SolveItSolveIt
1162
asked Jul 9 '18 at 1:24
SolveItSolveIt
1162
1162
bumped to the homepage by Community♦ 3 hours ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
bumped to the homepage by Community♦ 3 hours ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
3
$begingroup$
No, it means you have to train it more.
$endgroup$
– Vaalizaadeh
Jul 9 '18 at 1:36
1
$begingroup$
"less able to overfit" -- explain how it is that you are measuring this, and we can help more.
$endgroup$
– Scott
Jul 9 '18 at 4:11
add a comment |
3
$begingroup$
No, it means you have to train it more.
$endgroup$
– Vaalizaadeh
Jul 9 '18 at 1:36
1
$begingroup$
"less able to overfit" -- explain how it is that you are measuring this, and we can help more.
$endgroup$
– Scott
Jul 9 '18 at 4:11
3
3
$begingroup$
No, it means you have to train it more.
$endgroup$
– Vaalizaadeh
Jul 9 '18 at 1:36
$begingroup$
No, it means you have to train it more.
$endgroup$
– Vaalizaadeh
Jul 9 '18 at 1:36
1
1
$begingroup$
"less able to overfit" -- explain how it is that you are measuring this, and we can help more.
$endgroup$
– Scott
Jul 9 '18 at 4:11
$begingroup$
"less able to overfit" -- explain how it is that you are measuring this, and we can help more.
$endgroup$
– Scott
Jul 9 '18 at 4:11
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
It is not necessarily a red flag. Of course, without seeing the code, it is impossible to say that for sure.
What is likely happening here is that adding parameters to your model, it makes it harder for it to converge to some minimum. More parameters roughly mean that your model is able to explain "more complex stuff". And since you have a small amount of data, the explanation should remain rather simple. Therefore, your model is trying to explain something simple in a complicated way, and it might not be easy to do so.
Also, are you using dropout or regularization? If yes, this might also be an issue as these are explicitly use to avoid overfitting.
answered Jul 10 '18 at 12:52
Valentin CalommeValentin Calomme
1,295423
$endgroup$
add a comment |
Your Answer
StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
});
});
}, "mathjax-editing");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "557"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
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%2fdatascience.stackexchange.com%2fquestions%2f34174%2fis-it-a-red-flag-that-increasing-the-number-of-parameters-makes-the-model-less-a%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
It is not necessarily a red flag. Of course, without seeing the code, it is impossible to say that for sure.
What is likely happening here is that adding parameters to your model, it makes it harder for it to converge to some minimum. More parameters roughly mean that your model is able to explain "more complex stuff". And since you have a small amount of data, the explanation should remain rather simple. Therefore, your model is trying to explain something simple in a complicated way, and it might not be easy to do so.
Also, are you using dropout or regularization? If yes, this might also be an issue as these are explicitly use to avoid overfitting.
answered Jul 10 '18 at 12:52
Valentin CalommeValentin Calomme
1,295423
$endgroup$
add a comment |
$begingroup$
It is not necessarily a red flag. Of course, without seeing the code, it is impossible to say that for sure.
What is likely happening here is that adding parameters to your model, it makes it harder for it to converge to some minimum. More parameters roughly mean that your model is able to explain "more complex stuff". And since you have a small amount of data, the explanation should remain rather simple. Therefore, your model is trying to explain something simple in a complicated way, and it might not be easy to do so.
Also, are you using dropout or regularization? If yes, this might also be an issue as these are explicitly use to avoid overfitting.
answered Jul 10 '18 at 12:52
Valentin CalommeValentin Calomme
1,295423
$endgroup$
add a comment |
$begingroup$
It is not necessarily a red flag. Of course, without seeing the code, it is impossible to say that for sure.
What is likely happening here is that adding parameters to your model, it makes it harder for it to converge to some minimum. More parameters roughly mean that your model is able to explain "more complex stuff". And since you have a small amount of data, the explanation should remain rather simple. Therefore, your model is trying to explain something simple in a complicated way, and it might not be easy to do so.
Also, are you using dropout or regularization? If yes, this might also be an issue as these are explicitly use to avoid overfitting.
answered Jul 10 '18 at 12:52
Valentin CalommeValentin Calomme
1,295423
$endgroup$
It is not necessarily a red flag. Of course, without seeing the code, it is impossible to say that for sure.
What is likely happening here is that adding parameters to your model, it makes it harder for it to converge to some minimum. More parameters roughly mean that your model is able to explain "more complex stuff". And since you have a small amount of data, the explanation should remain rather simple. Therefore, your model is trying to explain something simple in a complicated way, and it might not be easy to do so.
Also, are you using dropout or regularization? If yes, this might also be an issue as these are explicitly use to avoid overfitting.
answered Jul 10 '18 at 12:52
Valentin CalommeValentin Calomme
1,295423
answered Jul 10 '18 at 12:52
Valentin CalommeValentin Calomme
1,295423
answered Jul 10 '18 at 12:52
Valentin CalommeValentin Calomme
1,295423
answered Jul 10 '18 at 12:52
Valentin CalommeValentin Calomme
1,295423
1,295423
add a comment |
add a comment |
Thanks for contributing an answer to Data Science Stack Exchange!
- 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.
Use MathJax to format equations. MathJax reference.
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%2fdatascience.stackexchange.com%2fquestions%2f34174%2fis-it-a-red-flag-that-increasing-the-number-of-parameters-makes-the-model-less-a%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
3
$begingroup$
No, it means you have to train it more.
$endgroup$
– Vaalizaadeh
Jul 9 '18 at 1:36
1
$begingroup$
"less able to overfit" -- explain how it is that you are measuring this, and we can help more.
$endgroup$
– Scott
Jul 9 '18 at 4:11