Trjtdtk

In musical terms, what properties are varied by the human voice to produce different words / syllables?

Mounting TV on a weird wall that has some material between the drywall and stud

Asymptotics question

Would color changing eyes affect vision?

"klopfte jemand" or "jemand klopfte"?

How to write capital alpha?

NERDTreeMenu Remapping

Can an iPhone 7 be made to function as a NFC Tag?

What is a more techy Technical Writer job title that isn't cutesy or confusing?

How much damage would a cupful of neutron star matter do to the Earth?

What is the "studentd" process?

Why do early math courses focus on the cross sections of a cone and not on other 3D objects?

How does light 'choose' between wave and particle behaviour?

What does 丫 mean? 丫是什么意思？

My mentor says to set image to Fine instead of RAW — how is this different from JPG?

Can you force honesty by using the Speak with Dead and Zone of Truth spells together?

Is openssl rand command cryptographically secure?

Are the endpoints of the domain of a function counted as critical points?

As a dual citizen, my US passport will expire one day after traveling to the US. Will this work?

What would you call this weird metallic apparatus that allows you to lift people?

How to change the tick of the color bar legend to black

How can I prevent/balance waiting and turtling as a response to cooldown mechanics

Moving a wrapfig vertically to encroach partially on a subsection title

Sally's older brother

How to set a newtwork with two objectives?

1

$begingroup$

Suppose I have a x_train, y1_train and y2_train.

I want to construct a network (such as simple MLP) to fit y1_train and to be low correlated with y2_train (or to fit -y2_train) simultaneously.

How could I achieve this goal? Is the custom loss function a good solution?

I use keras as my tool.

machine-learning keras

share|improve this question

edited Apr 4 at 5:04

Martin Thoma

6,7781657135

asked Apr 4 at 3:11

LiuHaoLiuHao

61

$endgroup$

add a comment | 

1

$begingroup$

Suppose I have a x_train, y1_train and y2_train.

I want to construct a network (such as simple MLP) to fit y1_train and to be low correlated with y2_train (or to fit -y2_train) simultaneously.

How could I achieve this goal? Is the custom loss function a good solution?

I use keras as my tool.

machine-learning keras

share|improve this question

edited Apr 4 at 5:04

Martin Thoma

6,7781657135

asked Apr 4 at 3:11

LiuHaoLiuHao

61

$endgroup$

add a comment | 

$begingroup$

Suppose I have a x_train, y1_train and y2_train.

I want to construct a network (such as simple MLP) to fit y1_train and to be low correlated with y2_train (or to fit -y2_train) simultaneously.

How could I achieve this goal? Is the custom loss function a good solution?

I use keras as my tool.

machine-learning keras

share|improve this question

edited Apr 4 at 5:04

Martin Thoma

6,7781657135

asked Apr 4 at 3:11

LiuHaoLiuHao

61

$endgroup$

share|improve this question

edited Apr 4 at 5:04

Martin Thoma

6,7781657135

asked Apr 4 at 3:11

LiuHaoLiuHao

61

share|improve this question

edited Apr 4 at 5:04

Martin Thoma

6,7781657135

asked Apr 4 at 3:11

LiuHaoLiuHao

61

edited Apr 4 at 5:04

Martin Thoma

6,7781657135

edited Apr 4 at 5:04

Martin Thoma

6,7781657135

asked Apr 4 at 3:11

LiuHaoLiuHao

61

asked Apr 4 at 3:11

LiuHaoLiuHao

61

1 Answer
1

active

oldest

votes

1

$begingroup$

So this problem is less of a Deep learning problem and more of a logical problem. Your y1_train and y2_train can be modelled along with a pointer label that points what output to be considered in the output. Lets say we create the concatenated output as follows:

[[0/1],[y1_train], [y2_train]] 

Where 0 could represent weather the label to be selected is y1 or y2 and so on.

But if you are planning to create a little more complex output and train different outputs on different loss functions, here is an article you should refer to Multiple output tutorial/examples and Custom Loss Function for Unequal Weighted Multiple-Output Node Regression

share|improve this answer

answered Apr 4 at 4:59

thanatozthanatoz

689421

$endgroup$

add a comment | 

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
);



);

draft saved

draft discarded

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

Name

Email

Required, but never shown

StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f48565%2fhow-to-set-a-newtwork-with-two-objectives%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

1

$begingroup$

So this problem is less of a Deep learning problem and more of a logical problem. Your y1_train and y2_train can be modelled along with a pointer label that points what output to be considered in the output. Lets say we create the concatenated output as follows:

[[0/1],[y1_train], [y2_train]] 

Where 0 could represent weather the label to be selected is y1 or y2 and so on.

But if you are planning to create a little more complex output and train different outputs on different loss functions, here is an article you should refer to Multiple output tutorial/examples and Custom Loss Function for Unequal Weighted Multiple-Output Node Regression

share|improve this answer

answered Apr 4 at 4:59

thanatozthanatoz

689421

$endgroup$

add a comment | 

1

$begingroup$

So this problem is less of a Deep learning problem and more of a logical problem. Your y1_train and y2_train can be modelled along with a pointer label that points what output to be considered in the output. Lets say we create the concatenated output as follows:

[[0/1],[y1_train], [y2_train]] 

Where 0 could represent weather the label to be selected is y1 or y2 and so on.

But if you are planning to create a little more complex output and train different outputs on different loss functions, here is an article you should refer to Multiple output tutorial/examples and Custom Loss Function for Unequal Weighted Multiple-Output Node Regression

share|improve this answer

answered Apr 4 at 4:59

thanatozthanatoz

689421

$endgroup$

add a comment | 

$begingroup$

So this problem is less of a Deep learning problem and more of a logical problem. Your y1_train and y2_train can be modelled along with a pointer label that points what output to be considered in the output. Lets say we create the concatenated output as follows:

[[0/1],[y1_train], [y2_train]] 

Where 0 could represent weather the label to be selected is y1 or y2 and so on.

But if you are planning to create a little more complex output and train different outputs on different loss functions, here is an article you should refer to Multiple output tutorial/examples and Custom Loss Function for Unequal Weighted Multiple-Output Node Regression

share|improve this answer

answered Apr 4 at 4:59

thanatozthanatoz

689421

$endgroup$

[[0/1],[y1_train], [y2_train]] 

share|improve this answer

answered Apr 4 at 4:59

thanatozthanatoz

689421

answered Apr 4 at 4:59

thanatozthanatoz

689421

answered Apr 4 at 4:59

thanatozthanatoz

689421