Backpropagation of a Neural Network containing Rolling Tensors and an Input Layer that is not at the Bottom...
I am currently creating a neural network for a side-project I am working on. I do not have the code ready, however for my basic structure, I was wondering if the following is possible / allowed with Neural Networks using Tensorflow.
My input layer is not the lowest layer of my neural network, and I am wondering if this will still allow the network to train properly using backpropagation. Essentially I would like my input layer to control how much a certain layer should be rolled via using the tf.roll, with my input layer controlling the amount of shift. In addition, there will be a placeholder layer that will be used as a mask on our rolled layer, prior to the input.
Essentially, my neural network will look as follows:
Hidden layer -> Hidden layer -> Hidden layer/"Output Layer" -> Input Layer That Rolls the previous layer -> Input Layer that Masks part of the previous layer -> Transformation -> Error
As you can see, all of my weights are "below" the input layer, and because of this I am unsure if gradient descent will work properly. The reason why it is designed this way is because my "Output Layer" is a Fourier transform, and my Input layer is providing a shift in the Fourier space, and then later converted into an audio signal. I am then using a spectrogram to compute the error in my output.
Will I still be able to use backpropagation in a design like this? Essentially everything "above" the input layer are constant transformations, and because of this in addition to the tf.roll, will backprop still work? Thank you so much!
python tensorflow networking backpropagation
New contributor
add a comment |
I am currently creating a neural network for a side-project I am working on. I do not have the code ready, however for my basic structure, I was wondering if the following is possible / allowed with Neural Networks using Tensorflow.
My input layer is not the lowest layer of my neural network, and I am wondering if this will still allow the network to train properly using backpropagation. Essentially I would like my input layer to control how much a certain layer should be rolled via using the tf.roll, with my input layer controlling the amount of shift. In addition, there will be a placeholder layer that will be used as a mask on our rolled layer, prior to the input.
Essentially, my neural network will look as follows:
Hidden layer -> Hidden layer -> Hidden layer/"Output Layer" -> Input Layer That Rolls the previous layer -> Input Layer that Masks part of the previous layer -> Transformation -> Error
As you can see, all of my weights are "below" the input layer, and because of this I am unsure if gradient descent will work properly. The reason why it is designed this way is because my "Output Layer" is a Fourier transform, and my Input layer is providing a shift in the Fourier space, and then later converted into an audio signal. I am then using a spectrogram to compute the error in my output.
Will I still be able to use backpropagation in a design like this? Essentially everything "above" the input layer are constant transformations, and because of this in addition to the tf.roll, will backprop still work? Thank you so much!
python tensorflow networking backpropagation
New contributor
add a comment |
I am currently creating a neural network for a side-project I am working on. I do not have the code ready, however for my basic structure, I was wondering if the following is possible / allowed with Neural Networks using Tensorflow.
My input layer is not the lowest layer of my neural network, and I am wondering if this will still allow the network to train properly using backpropagation. Essentially I would like my input layer to control how much a certain layer should be rolled via using the tf.roll, with my input layer controlling the amount of shift. In addition, there will be a placeholder layer that will be used as a mask on our rolled layer, prior to the input.
Essentially, my neural network will look as follows:
Hidden layer -> Hidden layer -> Hidden layer/"Output Layer" -> Input Layer That Rolls the previous layer -> Input Layer that Masks part of the previous layer -> Transformation -> Error
As you can see, all of my weights are "below" the input layer, and because of this I am unsure if gradient descent will work properly. The reason why it is designed this way is because my "Output Layer" is a Fourier transform, and my Input layer is providing a shift in the Fourier space, and then later converted into an audio signal. I am then using a spectrogram to compute the error in my output.
Will I still be able to use backpropagation in a design like this? Essentially everything "above" the input layer are constant transformations, and because of this in addition to the tf.roll, will backprop still work? Thank you so much!
python tensorflow networking backpropagation
New contributor
I am currently creating a neural network for a side-project I am working on. I do not have the code ready, however for my basic structure, I was wondering if the following is possible / allowed with Neural Networks using Tensorflow.
My input layer is not the lowest layer of my neural network, and I am wondering if this will still allow the network to train properly using backpropagation. Essentially I would like my input layer to control how much a certain layer should be rolled via using the tf.roll, with my input layer controlling the amount of shift. In addition, there will be a placeholder layer that will be used as a mask on our rolled layer, prior to the input.
Essentially, my neural network will look as follows:
Hidden layer -> Hidden layer -> Hidden layer/"Output Layer" -> Input Layer That Rolls the previous layer -> Input Layer that Masks part of the previous layer -> Transformation -> Error
As you can see, all of my weights are "below" the input layer, and because of this I am unsure if gradient descent will work properly. The reason why it is designed this way is because my "Output Layer" is a Fourier transform, and my Input layer is providing a shift in the Fourier space, and then later converted into an audio signal. I am then using a spectrogram to compute the error in my output.
Will I still be able to use backpropagation in a design like this? Essentially everything "above" the input layer are constant transformations, and because of this in addition to the tf.roll, will backprop still work? Thank you so much!
python tensorflow networking backpropagation
python tensorflow networking backpropagation
New contributor
New contributor
New contributor
asked 10 hours ago
Ryan Kashi
1
1
New contributor
New contributor
add a comment |
add a comment |
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
});
}
});
Ryan Kashi is a new contributor. Be nice, and check out our Code of Conduct.
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%2f53942495%2fbackpropagation-of-a-neural-network-containing-rolling-tensors-and-an-input-laye%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
Ryan Kashi is a new contributor. Be nice, and check out our Code of Conduct.
Ryan Kashi is a new contributor. Be nice, and check out our Code of Conduct.
Ryan Kashi is a new contributor. Be nice, and check out our Code of Conduct.
Ryan Kashi is a new contributor. Be nice, and check out our Code of Conduct.
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.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- 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%2f53942495%2fbackpropagation-of-a-neural-network-containing-rolling-tensors-and-an-input-laye%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