Why not mixing original training in favor of Pseudo-rehearsal?
$begingroup$
In multiple task transfer training, I just learnt that Pseudo-rehearsal can be used to solve the problem of 'catastrophic forgetting' problem, i.e. NN forgets the original generalization while learning the new task. In Pseudo rehearsal, it is suggested that mixing the new training data with the data tagged by the original model and then using the combined data to train a new model.
My question is that, instead of using the original model to produce tagged data, why not just adding the new data to the original gold standard training data to produce the new training data? The reason is that the data produced by the original model won't be gold standard. It's noisy.
transfer-learning
asked 9 mins ago
user697911user697911
1111
$endgroup$
add a comment |
$begingroup$
In multiple task transfer training, I just learnt that Pseudo-rehearsal can be used to solve the problem of 'catastrophic forgetting' problem, i.e. NN forgets the original generalization while learning the new task. In Pseudo rehearsal, it is suggested that mixing the new training data with the data tagged by the original model and then using the combined data to train a new model.
My question is that, instead of using the original model to produce tagged data, why not just adding the new data to the original gold standard training data to produce the new training data? The reason is that the data produced by the original model won't be gold standard. It's noisy.
transfer-learning
asked 9 mins ago
user697911user697911
1111
$endgroup$
add a comment |
$begingroup$
In multiple task transfer training, I just learnt that Pseudo-rehearsal can be used to solve the problem of 'catastrophic forgetting' problem, i.e. NN forgets the original generalization while learning the new task. In Pseudo rehearsal, it is suggested that mixing the new training data with the data tagged by the original model and then using the combined data to train a new model.
My question is that, instead of using the original model to produce tagged data, why not just adding the new data to the original gold standard training data to produce the new training data? The reason is that the data produced by the original model won't be gold standard. It's noisy.
transfer-learning
asked 9 mins ago
user697911user697911
1111
$endgroup$
In multiple task transfer training, I just learnt that Pseudo-rehearsal can be used to solve the problem of 'catastrophic forgetting' problem, i.e. NN forgets the original generalization while learning the new task. In Pseudo rehearsal, it is suggested that mixing the new training data with the data tagged by the original model and then using the combined data to train a new model.
My question is that, instead of using the original model to produce tagged data, why not just adding the new data to the original gold standard training data to produce the new training data? The reason is that the data produced by the original model won't be gold standard. It's noisy.
transfer-learning
transfer-learning
asked 9 mins ago
user697911user697911
1111
asked 9 mins ago
user697911user697911
1111
asked 9 mins ago
user697911user697911
1111
asked 9 mins ago
user697911user697911
1111
asked 9 mins ago
user697911user697911
1111
1111
add a comment |
add a comment |
0
active
oldest
votes
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%2f45596%2fwhy-not-mixing-original-training-in-favor-of-pseudo-rehearsal%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
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%2f45596%2fwhy-not-mixing-original-training-in-favor-of-pseudo-rehearsal%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
