Which accuracies to report in this case?
$begingroup$
I am new to ML research and to writing ML paper.
An ML research project resulted in a family of algorithms $A_i$. These algorithms transform certain type of data. This data is fed into a neural network $B$. The $B$ trained on data transformed by $A_i$ often outperforms the B trained on original data.
However, often the behaviour of test and train accuracy functions is a bit strange: the accuracy continues to rise for some time after the lowest train loss is reached.
Another problem is that for some datasets $B$ trains on transformed data in very few (often less than 10) epochs, and then the accuracy drops. But if learning rate is decreased, the network does not learn nearly as well.
Original paper of $B$ used one of the 10-fold splits to estimate the required number of epochs (usually several hundred), and the remaining 9 splits were used to compute test accuracy.
Which accuracies should I report?
Any other suggestions are welcome.
neural-network overfitting
asked yesterday
arystarcharystarch
1
New contributor
arystarch is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
I am new to ML research and to writing ML paper.
An ML research project resulted in a family of algorithms $A_i$. These algorithms transform certain type of data. This data is fed into a neural network $B$. The $B$ trained on data transformed by $A_i$ often outperforms the B trained on original data.
However, often the behaviour of test and train accuracy functions is a bit strange: the accuracy continues to rise for some time after the lowest train loss is reached.
Another problem is that for some datasets $B$ trains on transformed data in very few (often less than 10) epochs, and then the accuracy drops. But if learning rate is decreased, the network does not learn nearly as well.
Original paper of $B$ used one of the 10-fold splits to estimate the required number of epochs (usually several hundred), and the remaining 9 splits were used to compute test accuracy.
Which accuracies should I report?
Any other suggestions are welcome.
neural-network overfitting
asked yesterday
arystarcharystarch
1
New contributor
arystarch is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
I am new to ML research and to writing ML paper.
An ML research project resulted in a family of algorithms $A_i$. These algorithms transform certain type of data. This data is fed into a neural network $B$. The $B$ trained on data transformed by $A_i$ often outperforms the B trained on original data.
However, often the behaviour of test and train accuracy functions is a bit strange: the accuracy continues to rise for some time after the lowest train loss is reached.
Another problem is that for some datasets $B$ trains on transformed data in very few (often less than 10) epochs, and then the accuracy drops. But if learning rate is decreased, the network does not learn nearly as well.
Original paper of $B$ used one of the 10-fold splits to estimate the required number of epochs (usually several hundred), and the remaining 9 splits were used to compute test accuracy.
Which accuracies should I report?
Any other suggestions are welcome.
neural-network overfitting
asked yesterday
arystarcharystarch
1
New contributor
arystarch is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
I am new to ML research and to writing ML paper.
An ML research project resulted in a family of algorithms $A_i$. These algorithms transform certain type of data. This data is fed into a neural network $B$. The $B$ trained on data transformed by $A_i$ often outperforms the B trained on original data.
However, often the behaviour of test and train accuracy functions is a bit strange: the accuracy continues to rise for some time after the lowest train loss is reached.
Another problem is that for some datasets $B$ trains on transformed data in very few (often less than 10) epochs, and then the accuracy drops. But if learning rate is decreased, the network does not learn nearly as well.
Original paper of $B$ used one of the 10-fold splits to estimate the required number of epochs (usually several hundred), and the remaining 9 splits were used to compute test accuracy.
Which accuracies should I report?
Any other suggestions are welcome.
neural-network overfitting
neural-network overfitting
asked yesterday
arystarcharystarch
1
New contributor
arystarch is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
arystarcharystarch
1
New contributor
arystarch is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
arystarcharystarch
1
New contributor
arystarch is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
arystarcharystarch
1
asked yesterday
arystarcharystarch
1
1
New contributor
arystarch is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
arystarch is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
arystarch is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
add a comment |
add a comment |
0
active
oldest
votes
Your Answer
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
});
}
});
arystarch is a new contributor. Be nice, and check out our Code of Conduct.
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%2f49200%2fwhich-accuracies-to-report-in-this-case%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
arystarch is a new contributor. Be nice, and check out our Code of Conduct.
arystarch is a new contributor. Be nice, and check out our Code of Conduct.
arystarch is a new contributor. Be nice, and check out our Code of Conduct.
arystarch is a new contributor. Be nice, and check out our Code of Conduct.
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%2f49200%2fwhich-accuracies-to-report-in-this-case%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
