Scaling outputs in multi-hot encoding and using class weights
I have a recurrent neural network to classify sequential data.
Not all samples have the same relevance to the prediction, others include multiple classes at once. For example a sequence of words could be both class 0 and class 1.
[1,0,0], [0,1,0] -> [0.5,0.5,0]
Therefore i would like to blend class probabilities in my training data, using somewhat of a multi hot encoding. I feel like this approach just creates new (scaled) classes in instead of yielding better training results for existing classes.
When using this data as sample_weights for training this leads to very small classes, for example:
These three classes:
Class 0: [1.0,0.0,0.0]
Class 1: [0.0,1.0,0.0]
Class 2: [1.0,0.0,1.0]
become
Class 0: [1.0,0.0,0.0]
Class 1: [0.9,0.1,0.0]
..
Class 9: [0.0,1.0,0.0]
..
This is problematic because I would like to set the class_weights for just the three classes independent of the scaling according to their sample count.
Also: How can I do that in Keras?
python keras lstm recurrent-neural-network one-hot-encoding
asked Nov 23 '18 at 16:28
floridaflorida
135
add a comment |
I have a recurrent neural network to classify sequential data.
Not all samples have the same relevance to the prediction, others include multiple classes at once. For example a sequence of words could be both class 0 and class 1.
[1,0,0], [0,1,0] -> [0.5,0.5,0]
Therefore i would like to blend class probabilities in my training data, using somewhat of a multi hot encoding. I feel like this approach just creates new (scaled) classes in instead of yielding better training results for existing classes.
When using this data as sample_weights for training this leads to very small classes, for example:
These three classes:
Class 0: [1.0,0.0,0.0]
Class 1: [0.0,1.0,0.0]
Class 2: [1.0,0.0,1.0]
become
Class 0: [1.0,0.0,0.0]
Class 1: [0.9,0.1,0.0]
..
Class 9: [0.0,1.0,0.0]
..
This is problematic because I would like to set the class_weights for just the three classes independent of the scaling according to their sample count.
Also: How can I do that in Keras?
python keras lstm recurrent-neural-network one-hot-encoding
asked Nov 23 '18 at 16:28
floridaflorida
135
add a comment |
I have a recurrent neural network to classify sequential data.
Not all samples have the same relevance to the prediction, others include multiple classes at once. For example a sequence of words could be both class 0 and class 1.
[1,0,0], [0,1,0] -> [0.5,0.5,0]
Therefore i would like to blend class probabilities in my training data, using somewhat of a multi hot encoding. I feel like this approach just creates new (scaled) classes in instead of yielding better training results for existing classes.
When using this data as sample_weights for training this leads to very small classes, for example:
These three classes:
Class 0: [1.0,0.0,0.0]
Class 1: [0.0,1.0,0.0]
Class 2: [1.0,0.0,1.0]
become
Class 0: [1.0,0.0,0.0]
Class 1: [0.9,0.1,0.0]
..
Class 9: [0.0,1.0,0.0]
..
This is problematic because I would like to set the class_weights for just the three classes independent of the scaling according to their sample count.
Also: How can I do that in Keras?
python keras lstm recurrent-neural-network one-hot-encoding
asked Nov 23 '18 at 16:28
floridaflorida
135
I have a recurrent neural network to classify sequential data.
Not all samples have the same relevance to the prediction, others include multiple classes at once. For example a sequence of words could be both class 0 and class 1.
[1,0,0], [0,1,0] -> [0.5,0.5,0]
Therefore i would like to blend class probabilities in my training data, using somewhat of a multi hot encoding. I feel like this approach just creates new (scaled) classes in instead of yielding better training results for existing classes.
When using this data as sample_weights for training this leads to very small classes, for example:
These three classes:
Class 0: [1.0,0.0,0.0]
Class 1: [0.0,1.0,0.0]
Class 2: [1.0,0.0,1.0]
become
Class 0: [1.0,0.0,0.0]
Class 1: [0.9,0.1,0.0]
..
Class 9: [0.0,1.0,0.0]
..
This is problematic because I would like to set the class_weights for just the three classes independent of the scaling according to their sample count.
Also: How can I do that in Keras?
python keras lstm recurrent-neural-network one-hot-encoding
python keras lstm recurrent-neural-network one-hot-encoding
asked Nov 23 '18 at 16:28
floridaflorida
135
asked Nov 23 '18 at 16:28
floridaflorida
135
asked Nov 23 '18 at 16:28
floridaflorida
135
asked Nov 23 '18 at 16:28
floridaflorida
135
asked Nov 23 '18 at 16:28
floridaflorida
135
135
add a comment |
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
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: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
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%2fstackoverflow.com%2fquestions%2f53450132%2fscaling-outputs-in-multi-hot-encoding-and-using-class-weights%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 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.
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%2f53450132%2fscaling-outputs-in-multi-hot-encoding-and-using-class-weights%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
