correcting conditional and marginal distribution in transfer learningWhere to find pre-trained models for transfer learningMultimodal distribution and GANsTransfer learning: Poor performance with last layer replaceda simple way to test wether a tree-based classifier would transfer well to a target population?Is there any proven disadvantage of transfer learning for CNNs?Transfer learning by concatenating the last classification layerResource and useful tips on Transfer Learning in NLPParameter of Conditional Gaussian DistributionTransfer learning - small databaseHow to properly resize input images for transfer learning
Are cause and effect the same as in our Universe in a non-relativistic, Newtonian Universe in which the speed of light is infinite?
How can ping know if my host is down
Has the laser at Magurele, Romania reached a tenth of the Sun's power?
Why can't the Brexit deadlock in the UK parliament be solved with a plurality vote?
Does "he squandered his car on drink" sound natural?
Does Doodling or Improvising on the Piano Have Any Benefits?
How to convince somebody that he is fit for something else, but not this job?
What is going on with gets(stdin) on the site coderbyte?
How would you translate "more" for use as an interface button?
Microchip documentation does not label CAN buss pins on micro controller pinout diagram
Is this toilet slogan correct usage of the English language?
Pre-mixing cryogenic fuels and using only one fuel tank
Which Article Helped Get Rid of Technobabble in RPGs?
How does electrical safety system work on ISS?
Change the color of a single dot in `ddot` symbol
What kind of floor tile is this?
How do you make your own symbol when Detexify fails?
The IT department bottlenecks progress, how should I handle this?
Will number of steps recorded on FitBit/any fitness tracker add up distance in PokemonGo?
How to make money from a browser who sees 5 seconds into the future of any web page?
How to preserve electronics (computers, iPads and phones) for hundreds of years
How to explain what's wrong with this application of the chain rule?
Doesn't the system of the Supreme Court oppose justice?
PTIJ: Why is Haman obsessed with Bose?
correcting conditional and marginal distribution in transfer learning
Where to find pre-trained models for transfer learningMultimodal distribution and GANsTransfer learning: Poor performance with last layer replaceda simple way to test wether a tree-based classifier would transfer well to a target population?Is there any proven disadvantage of transfer learning for CNNs?Transfer learning by concatenating the last classification layerResource and useful tips on Transfer Learning in NLPParameter of Conditional Gaussian DistributionTransfer learning - small databaseHow to properly resize input images for transfer learning
$begingroup$
I understand that in case of transfer learning, we can have the target and the source data having different domain distributions. In such cases, authors in many papers suggest bringing the marginal and conditional distributions of the target and the source closer, i.e, minimize the difference between the marginal and conditional distributions. Can someone please help me understand this by giving an intuitive explanation for this? I am unable to understand what exactly the author means when he says by bringing the distributions closer? Explanations using visual representations would be helpful.
machine-learning probability transfer-learning
asked Jul 9 '18 at 7:23
DexterDexter
11
$endgroup$
bumped to the homepage by Community♦ 21 mins 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 understand that in case of transfer learning, we can have the target and the source data having different domain distributions. In such cases, authors in many papers suggest bringing the marginal and conditional distributions of the target and the source closer, i.e, minimize the difference between the marginal and conditional distributions. Can someone please help me understand this by giving an intuitive explanation for this? I am unable to understand what exactly the author means when he says by bringing the distributions closer? Explanations using visual representations would be helpful.
machine-learning probability transfer-learning
asked Jul 9 '18 at 7:23
DexterDexter
11
$endgroup$
bumped to the homepage by Community♦ 21 mins 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 understand that in case of transfer learning, we can have the target and the source data having different domain distributions. In such cases, authors in many papers suggest bringing the marginal and conditional distributions of the target and the source closer, i.e, minimize the difference between the marginal and conditional distributions. Can someone please help me understand this by giving an intuitive explanation for this? I am unable to understand what exactly the author means when he says by bringing the distributions closer? Explanations using visual representations would be helpful.
machine-learning probability transfer-learning
asked Jul 9 '18 at 7:23
DexterDexter
11
$endgroup$
I understand that in case of transfer learning, we can have the target and the source data having different domain distributions. In such cases, authors in many papers suggest bringing the marginal and conditional distributions of the target and the source closer, i.e, minimize the difference between the marginal and conditional distributions. Can someone please help me understand this by giving an intuitive explanation for this? I am unable to understand what exactly the author means when he says by bringing the distributions closer? Explanations using visual representations would be helpful.
machine-learning probability transfer-learning
machine-learning probability transfer-learning
asked Jul 9 '18 at 7:23
DexterDexter
11
asked Jul 9 '18 at 7:23
DexterDexter
11
edited Jul 10 '18 at 10:07
Dexter
asked Jul 9 '18 at 7:23
DexterDexter
11
asked Jul 9 '18 at 7:23
DexterDexter
11
asked Jul 9 '18 at 7:23
DexterDexter
11
11
bumped to the homepage by Community♦ 21 mins 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♦ 21 mins 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 |
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
Bringing the distributions closer means that we are trying to modify the source data usually by performing weights in the instances or in the features (or in both in hybrid algorithms) in order to make the weighted data more similar to the targer data. If we achieve that then we will be able to train a model considering also the source data, which usually has a larger size or it is well annotated in comparison with the target.
answered Feb 19 at 23:05
Christos KaratsalosChristos Karatsalos
51218
$endgroup$
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%2f34176%2fcorrecting-conditional-and-marginal-distribution-in-transfer-learning%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
$begingroup$
Bringing the distributions closer means that we are trying to modify the source data usually by performing weights in the instances or in the features (or in both in hybrid algorithms) in order to make the weighted data more similar to the targer data. If we achieve that then we will be able to train a model considering also the source data, which usually has a larger size or it is well annotated in comparison with the target.
answered Feb 19 at 23:05
Christos KaratsalosChristos Karatsalos
51218
$endgroup$
add a comment |
$begingroup$
Bringing the distributions closer means that we are trying to modify the source data usually by performing weights in the instances or in the features (or in both in hybrid algorithms) in order to make the weighted data more similar to the targer data. If we achieve that then we will be able to train a model considering also the source data, which usually has a larger size or it is well annotated in comparison with the target.
answered Feb 19 at 23:05
Christos KaratsalosChristos Karatsalos
51218
$endgroup$
add a comment |
$begingroup$
Bringing the distributions closer means that we are trying to modify the source data usually by performing weights in the instances or in the features (or in both in hybrid algorithms) in order to make the weighted data more similar to the targer data. If we achieve that then we will be able to train a model considering also the source data, which usually has a larger size or it is well annotated in comparison with the target.
answered Feb 19 at 23:05
Christos KaratsalosChristos Karatsalos
51218
$endgroup$
Bringing the distributions closer means that we are trying to modify the source data usually by performing weights in the instances or in the features (or in both in hybrid algorithms) in order to make the weighted data more similar to the targer data. If we achieve that then we will be able to train a model considering also the source data, which usually has a larger size or it is well annotated in comparison with the target.
answered Feb 19 at 23:05
Christos KaratsalosChristos Karatsalos
51218
answered Feb 19 at 23:05
Christos KaratsalosChristos Karatsalos
51218
answered Feb 19 at 23:05
Christos KaratsalosChristos Karatsalos
51218
answered Feb 19 at 23:05
Christos KaratsalosChristos Karatsalos
51218
51218
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%2f34176%2fcorrecting-conditional-and-marginal-distribution-in-transfer-learning%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
