Gradient of NN output with respect to inputs
$begingroup$
I've trained a neural net on a problem where multiple inputs can be mapped to the same output. I'd like to use this NN to go from an output to an input i.e. given an output vector $y$, I want to find an input $x$ such that the NN returns some $z$ close to the given output $y$ when fed input $x$. I was thinking of using gradient descent to do this - do any of the common deep learning APIs let you take gradients of NNs with respect to their inputs? I've looked around and haven't found anything, but figured I'd check here before moving forward.
machine-learning neural-network deep-learning tensorflow pytorch
$endgroup$
bumped to the homepage by Community♦ 10 hours 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've trained a neural net on a problem where multiple inputs can be mapped to the same output. I'd like to use this NN to go from an output to an input i.e. given an output vector $y$, I want to find an input $x$ such that the NN returns some $z$ close to the given output $y$ when fed input $x$. I was thinking of using gradient descent to do this - do any of the common deep learning APIs let you take gradients of NNs with respect to their inputs? I've looked around and haven't found anything, but figured I'd check here before moving forward.
machine-learning neural-network deep-learning tensorflow pytorch
$endgroup$
bumped to the homepage by Community♦ 10 hours 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've trained a neural net on a problem where multiple inputs can be mapped to the same output. I'd like to use this NN to go from an output to an input i.e. given an output vector $y$, I want to find an input $x$ such that the NN returns some $z$ close to the given output $y$ when fed input $x$. I was thinking of using gradient descent to do this - do any of the common deep learning APIs let you take gradients of NNs with respect to their inputs? I've looked around and haven't found anything, but figured I'd check here before moving forward.
machine-learning neural-network deep-learning tensorflow pytorch
$endgroup$
I've trained a neural net on a problem where multiple inputs can be mapped to the same output. I'd like to use this NN to go from an output to an input i.e. given an output vector $y$, I want to find an input $x$ such that the NN returns some $z$ close to the given output $y$ when fed input $x$. I was thinking of using gradient descent to do this - do any of the common deep learning APIs let you take gradients of NNs with respect to their inputs? I've looked around and haven't found anything, but figured I'd check here before moving forward.
machine-learning neural-network deep-learning tensorflow pytorch
machine-learning neural-network deep-learning tensorflow pytorch
asked Jan 9 at 1:15
user65561user65561
1
1
bumped to the homepage by Community♦ 10 hours 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♦ 10 hours 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 |
2 Answers
2
active
oldest
votes
$begingroup$
Yes there is. This is called "back-propagation to the input". I invite you to read this awesome blog which rely on lucid. You will see some codes on their notebooks.
$endgroup$
$begingroup$
From the linked blog: "Neural networks are, generally speaking, differentiable with respect to their inputs. If we want to find out what kind of input would cause a certain behavior — whether that’s an internal neuron firing or the final output behavior — we can use derivatives to iteratively tweak the input towards that goal" -- seems to validate OP's idea!
$endgroup$
– Imran
Jan 11 at 21:59
add a comment |
$begingroup$
iNNvestigate is a very powerful and well-written library for inspecting the neural networks. Among others, it includes the gradient
method.
However, if you want to synthesize an input that will cause the network to produce certain output - this technique is known as code inversion. Follow the paper by Mahendran et al. for more details. I found the following implementations for it:
- https://github.com/ruthcfong/invert
- http://www.robots.ox.ac.uk/~vgg/research/invrep/index.html
$endgroup$
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%2f43699%2fgradient-of-nn-output-with-respect-to-inputs%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
2 Answers
2
active
oldest
votes
2 Answers
2
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
Yes there is. This is called "back-propagation to the input". I invite you to read this awesome blog which rely on lucid. You will see some codes on their notebooks.
$endgroup$
$begingroup$
From the linked blog: "Neural networks are, generally speaking, differentiable with respect to their inputs. If we want to find out what kind of input would cause a certain behavior — whether that’s an internal neuron firing or the final output behavior — we can use derivatives to iteratively tweak the input towards that goal" -- seems to validate OP's idea!
$endgroup$
– Imran
Jan 11 at 21:59
add a comment |
$begingroup$
Yes there is. This is called "back-propagation to the input". I invite you to read this awesome blog which rely on lucid. You will see some codes on their notebooks.
$endgroup$
$begingroup$
From the linked blog: "Neural networks are, generally speaking, differentiable with respect to their inputs. If we want to find out what kind of input would cause a certain behavior — whether that’s an internal neuron firing or the final output behavior — we can use derivatives to iteratively tweak the input towards that goal" -- seems to validate OP's idea!
$endgroup$
– Imran
Jan 11 at 21:59
add a comment |
$begingroup$
Yes there is. This is called "back-propagation to the input". I invite you to read this awesome blog which rely on lucid. You will see some codes on their notebooks.
$endgroup$
Yes there is. This is called "back-propagation to the input". I invite you to read this awesome blog which rely on lucid. You will see some codes on their notebooks.
answered Jan 11 at 14:49
Adrien DAdrien D
4636
4636
$begingroup$
From the linked blog: "Neural networks are, generally speaking, differentiable with respect to their inputs. If we want to find out what kind of input would cause a certain behavior — whether that’s an internal neuron firing or the final output behavior — we can use derivatives to iteratively tweak the input towards that goal" -- seems to validate OP's idea!
$endgroup$
– Imran
Jan 11 at 21:59
add a comment |
$begingroup$
From the linked blog: "Neural networks are, generally speaking, differentiable with respect to their inputs. If we want to find out what kind of input would cause a certain behavior — whether that’s an internal neuron firing or the final output behavior — we can use derivatives to iteratively tweak the input towards that goal" -- seems to validate OP's idea!
$endgroup$
– Imran
Jan 11 at 21:59
$begingroup$
From the linked blog: "Neural networks are, generally speaking, differentiable with respect to their inputs. If we want to find out what kind of input would cause a certain behavior — whether that’s an internal neuron firing or the final output behavior — we can use derivatives to iteratively tweak the input towards that goal" -- seems to validate OP's idea!
$endgroup$
– Imran
Jan 11 at 21:59
$begingroup$
From the linked blog: "Neural networks are, generally speaking, differentiable with respect to their inputs. If we want to find out what kind of input would cause a certain behavior — whether that’s an internal neuron firing or the final output behavior — we can use derivatives to iteratively tweak the input towards that goal" -- seems to validate OP's idea!
$endgroup$
– Imran
Jan 11 at 21:59
add a comment |
$begingroup$
iNNvestigate is a very powerful and well-written library for inspecting the neural networks. Among others, it includes the gradient
method.
However, if you want to synthesize an input that will cause the network to produce certain output - this technique is known as code inversion. Follow the paper by Mahendran et al. for more details. I found the following implementations for it:
- https://github.com/ruthcfong/invert
- http://www.robots.ox.ac.uk/~vgg/research/invrep/index.html
$endgroup$
add a comment |
$begingroup$
iNNvestigate is a very powerful and well-written library for inspecting the neural networks. Among others, it includes the gradient
method.
However, if you want to synthesize an input that will cause the network to produce certain output - this technique is known as code inversion. Follow the paper by Mahendran et al. for more details. I found the following implementations for it:
- https://github.com/ruthcfong/invert
- http://www.robots.ox.ac.uk/~vgg/research/invrep/index.html
$endgroup$
add a comment |
$begingroup$
iNNvestigate is a very powerful and well-written library for inspecting the neural networks. Among others, it includes the gradient
method.
However, if you want to synthesize an input that will cause the network to produce certain output - this technique is known as code inversion. Follow the paper by Mahendran et al. for more details. I found the following implementations for it:
- https://github.com/ruthcfong/invert
- http://www.robots.ox.ac.uk/~vgg/research/invrep/index.html
$endgroup$
iNNvestigate is a very powerful and well-written library for inspecting the neural networks. Among others, it includes the gradient
method.
However, if you want to synthesize an input that will cause the network to produce certain output - this technique is known as code inversion. Follow the paper by Mahendran et al. for more details. I found the following implementations for it:
- https://github.com/ruthcfong/invert
- http://www.robots.ox.ac.uk/~vgg/research/invrep/index.html
answered Jan 11 at 20:56
Dmytro PrylipkoDmytro Prylipko
4387
4387
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%2f43699%2fgradient-of-nn-output-with-respect-to-inputs%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