Can anyone explain the reasoning behind this post?2019 Community Moderator ElectionWhy could my SVR prediction be offset, but still follow the actual pattern?Type-II error in Hypothesis TestingWhy do we convert skewed data into a normal distributionPrediction Intervals Using XGBoostEpoch greedy algorithm for contextual banditsCreating a posterior distribution for classic coin flipping in python using grid searchNeural network only converges when data cloud is close to 0High RMSE and MAE and low MAPELink Prediction based Similarity IndicesIntuitive Explanation of R-squared
A Rare Riley Riddle
Unreliable Magic - Is it worth it?
Do the temporary hit points from the Battlerager barbarian's Reckless Abandon stack if I make multiple attacks on my turn?
Implement the Thanos sorting algorithm
Is there a good way to store credentials outside of a password manager?
Short story about space worker geeks who zone out by 'listening' to radiation from stars
Is a stroke of luck acceptable after a series of unfavorable events?
Anatomically Correct Strange Women In Ponds Distributing Swords
How do we know the LHC results are robust?
How can a function with a hole (removable discontinuity) equal a function with no hole?
Would a high gravity rocky planet be guaranteed to have an atmosphere?
Term for the "extreme-extension" version of a straw man fallacy?
Avoiding estate tax by giving multiple gifts
How does it work when somebody invests in my business?
How to create a 32-bit integer from eight (8) 4-bit integers?
How to pronounce the slash sign
India just shot down a satellite from the ground. At what altitude range is the resulting debris field?
Lay out the Carpet
Trouble understanding the speech of overseas colleagues
What is the intuitive meaning of having a linear relationship between the logs of two variables?
How to be diplomatic in refusing to write code that breaches the privacy of our users
How did Arya survive the stabbing?
What does "Allow AS in" do in BGP?
How do I rename a Linux host without needing to reboot for the rename to take effect?
Can anyone explain the reasoning behind this post?
2019 Community Moderator ElectionWhy could my SVR prediction be offset, but still follow the actual pattern?Type-II error in Hypothesis TestingWhy do we convert skewed data into a normal distributionPrediction Intervals Using XGBoostEpoch greedy algorithm for contextual banditsCreating a posterior distribution for classic coin flipping in python using grid searchNeural network only converges when data cloud is close to 0High RMSE and MAE and low MAPELink Prediction based Similarity IndicesIntuitive Explanation of R-squared
$begingroup$
I am reading THIS blog post,
and I do not understand the logic behind this part:
Why is the relu here max(0, Xavg - X) ? And even so, it does not really explain the values obtained in the two situations where X1 = X2 = 0, X1 = 1 and X2 = 0, and X1 = X2 = 1.
Can someone please explain this in more detail?
predictive-modeling regression statistics
asked Feb 20 at 10:39
QubixQubix
1114
$endgroup$
add a comment |
$begingroup$
I am reading THIS blog post,
and I do not understand the logic behind this part:
Why is the relu here max(0, Xavg - X) ? And even so, it does not really explain the values obtained in the two situations where X1 = X2 = 0, X1 = 1 and X2 = 0, and X1 = X2 = 1.
Can someone please explain this in more detail?
predictive-modeling regression statistics
asked Feb 20 at 10:39
QubixQubix
1114
$endgroup$
add a comment |
$begingroup$
I am reading THIS blog post,
and I do not understand the logic behind this part:
Why is the relu here max(0, Xavg - X) ? And even so, it does not really explain the values obtained in the two situations where X1 = X2 = 0, X1 = 1 and X2 = 0, and X1 = X2 = 1.
Can someone please explain this in more detail?
predictive-modeling regression statistics
asked Feb 20 at 10:39
QubixQubix
1114
$endgroup$
I am reading THIS blog post,
and I do not understand the logic behind this part:
Why is the relu here max(0, Xavg - X) ? And even so, it does not really explain the values obtained in the two situations where X1 = X2 = 0, X1 = 1 and X2 = 0, and X1 = X2 = 1.
Can someone please explain this in more detail?
predictive-modeling regression statistics
predictive-modeling regression statistics
asked Feb 20 at 10:39
QubixQubix
1114
asked Feb 20 at 10:39
QubixQubix
1114
asked Feb 20 at 10:39
QubixQubix
1114
asked Feb 20 at 10:39
QubixQubix
1114
asked Feb 20 at 10:39
QubixQubix
1114
1114
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
"Weight of 4" seems to be the key thing you're missing. Translating a little, the neuron's value is $operatornamerelu(5-4x_1-4x_2)$.
Oh, and there seems to be a typo in the post:
"Then, if X2 also gets switched to 0 1,"
answered Feb 20 at 15:11
Ben ReinigerBen Reiniger
33319
$endgroup$
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%2f45865%2fcan-anyone-explain-the-reasoning-behind-this-post%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
$begingroup$
"Weight of 4" seems to be the key thing you're missing. Translating a little, the neuron's value is $operatornamerelu(5-4x_1-4x_2)$.
Oh, and there seems to be a typo in the post:
"Then, if X2 also gets switched to 0 1,"
answered Feb 20 at 15:11
Ben ReinigerBen Reiniger
33319
$endgroup$
add a comment |
$begingroup$
"Weight of 4" seems to be the key thing you're missing. Translating a little, the neuron's value is $operatornamerelu(5-4x_1-4x_2)$.
Oh, and there seems to be a typo in the post:
"Then, if X2 also gets switched to 0 1,"
answered Feb 20 at 15:11
Ben ReinigerBen Reiniger
33319
$endgroup$
add a comment |
$begingroup$
"Weight of 4" seems to be the key thing you're missing. Translating a little, the neuron's value is $operatornamerelu(5-4x_1-4x_2)$.
Oh, and there seems to be a typo in the post:
"Then, if X2 also gets switched to 0 1,"
answered Feb 20 at 15:11
Ben ReinigerBen Reiniger
33319
$endgroup$
"Weight of 4" seems to be the key thing you're missing. Translating a little, the neuron's value is $operatornamerelu(5-4x_1-4x_2)$.
Oh, and there seems to be a typo in the post:
"Then, if X2 also gets switched to 0 1,"
answered Feb 20 at 15:11
Ben ReinigerBen Reiniger
33319
answered Feb 20 at 15:11
Ben ReinigerBen Reiniger
33319
answered Feb 20 at 15:11
Ben ReinigerBen Reiniger
33319
answered Feb 20 at 15:11
Ben ReinigerBen Reiniger
33319
33319
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%2f45865%2fcan-anyone-explain-the-reasoning-behind-this-post%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
