Why does a filter need to be applied to the output of the input gate before cell state is added to? Announcing the arrival of Valued Associate #679: Cesar Manara Planned maintenance scheduled April 17/18, 2019 at 00:00UTC (8:00pm US/Eastern) 2019 Moderator Election Q&A - Questionnaire 2019 Community Moderator Election ResultsLSTM Weight Matrix InterpretationForget Layer in a Recurrent Neural Network (RNN) -Trying to create an RNN with one character memoryCustom c++ LSTM slows down at 0.36 cost is usual?In a convolutional neural network (CNN), when convolving the image, is the operation used the dot product or the sum of element-wise multiplication?How is the LSTM RNN forget gate calculated?How to define the shape of hidden and meory state in Numpy, keras?LSTM Produces Random PredictionsThe memorisation capacity of an LSTM (real numbers)
How to market an anarchic city as a tourism spot to people living in civilized areas?
I'm having difficulty getting my players to do stuff in a sandbox campaign
Replacing HDD with SSD; what about non-APFS/APFS?
What loss function to use when labels are probabilities?
Antler Helmet: Can it work?
Can smartphones with the same camera sensor have different image quality?
Single author papers against my advisor's will?
The following signatures were invalid: EXPKEYSIG 1397BC53640DB551
New Order #5: where Fibonacci and Beatty meet at Wythoff
What to do with post with dry rot?
Who can trigger ship-wide alerts in Star Trek?
How to politely respond to generic emails requesting a PhD/job in my lab? Without wasting too much time
How can I make names more distinctive without making them longer?
Why does this iterative way of solving of equation work?
How do I automatically answer y in bash script?
Estimate capacitor parameters
What LEGO pieces have "real-world" functionality?
Why use gamma over alpha radiation?
How should I respond to a player wanting to catch a sword between their hands?
Active filter with series inductor and resistor - do these exist?
What do I do if technical issues prevent me from filing my return on time?
Using "nakedly" instead of "with nothing on"
What would be Julian Assange's expected punishment, on the current English criminal law?
Why don't the Weasley twins use magic outside of school if the Trace can only find the location of spells cast?
Why does a filter need to be applied to the output of the input gate before cell state is added to?
Announcing the arrival of Valued Associate #679: Cesar Manara
Planned maintenance scheduled April 17/18, 2019 at 00:00UTC (8:00pm US/Eastern)
2019 Moderator Election Q&A - Questionnaire
2019 Community Moderator Election ResultsLSTM Weight Matrix InterpretationForget Layer in a Recurrent Neural Network (RNN) -Trying to create an RNN with one character memoryCustom c++ LSTM slows down at 0.36 cost is usual?In a convolutional neural network (CNN), when convolving the image, is the operation used the dot product or the sum of element-wise multiplication?How is the LSTM RNN forget gate calculated?How to define the shape of hidden and meory state in Numpy, keras?LSTM Produces Random PredictionsThe memorisation capacity of an LSTM (real numbers)
$begingroup$
In a neural network there are 4 gates: input, output, forget and a gate whose output performs element wise multiplication with the output of the input gate, which is added to the cell state (I don't know the name of this gate, but it's the one in the below picture with the output C_tilde).
Why is the addition of the C_tilde gate required in the model? In order to allow the input gate to subtract from the cell state, we could change the activation function that results in i_t from sigmoid to tanh and remove the C_tilde gate.
My reasoning is that the input gate already has a weight matrix W_i that can is being multiplied to the input gate's input, hence it already does filtering. However, when C_tilde is multiplied with i_t that seems to be another unnecessary filter.
My proposed input gate would then be i_t = tanh(W_i * [h_t-1, x_t] + b_i) and i_t would directly be added to C_t (C_t = f_t * C_t + i_t rather than C_t = f_t * C_t + i_t * C_tilde_t).
machine-learning neural-network deep-learning lstm recurrent-neural-net
asked Jul 13 '18 at 0:26
Mar DevMar Dev
1061
$endgroup$
bumped to the homepage by Community♦ 52 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 |
$begingroup$
In a neural network there are 4 gates: input, output, forget and a gate whose output performs element wise multiplication with the output of the input gate, which is added to the cell state (I don't know the name of this gate, but it's the one in the below picture with the output C_tilde).
Why is the addition of the C_tilde gate required in the model? In order to allow the input gate to subtract from the cell state, we could change the activation function that results in i_t from sigmoid to tanh and remove the C_tilde gate.
My reasoning is that the input gate already has a weight matrix W_i that can is being multiplied to the input gate's input, hence it already does filtering. However, when C_tilde is multiplied with i_t that seems to be another unnecessary filter.
My proposed input gate would then be i_t = tanh(W_i * [h_t-1, x_t] + b_i) and i_t would directly be added to C_t (C_t = f_t * C_t + i_t rather than C_t = f_t * C_t + i_t * C_tilde_t).
machine-learning neural-network deep-learning lstm recurrent-neural-net
asked Jul 13 '18 at 0:26
Mar DevMar Dev
1061
$endgroup$
bumped to the homepage by Community♦ 52 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 |
$begingroup$
In a neural network there are 4 gates: input, output, forget and a gate whose output performs element wise multiplication with the output of the input gate, which is added to the cell state (I don't know the name of this gate, but it's the one in the below picture with the output C_tilde).
Why is the addition of the C_tilde gate required in the model? In order to allow the input gate to subtract from the cell state, we could change the activation function that results in i_t from sigmoid to tanh and remove the C_tilde gate.
My reasoning is that the input gate already has a weight matrix W_i that can is being multiplied to the input gate's input, hence it already does filtering. However, when C_tilde is multiplied with i_t that seems to be another unnecessary filter.
My proposed input gate would then be i_t = tanh(W_i * [h_t-1, x_t] + b_i) and i_t would directly be added to C_t (C_t = f_t * C_t + i_t rather than C_t = f_t * C_t + i_t * C_tilde_t).
machine-learning neural-network deep-learning lstm recurrent-neural-net
asked Jul 13 '18 at 0:26
Mar DevMar Dev
1061
$endgroup$
In a neural network there are 4 gates: input, output, forget and a gate whose output performs element wise multiplication with the output of the input gate, which is added to the cell state (I don't know the name of this gate, but it's the one in the below picture with the output C_tilde).
Why is the addition of the C_tilde gate required in the model? In order to allow the input gate to subtract from the cell state, we could change the activation function that results in i_t from sigmoid to tanh and remove the C_tilde gate.
My reasoning is that the input gate already has a weight matrix W_i that can is being multiplied to the input gate's input, hence it already does filtering. However, when C_tilde is multiplied with i_t that seems to be another unnecessary filter.
My proposed input gate would then be i_t = tanh(W_i * [h_t-1, x_t] + b_i) and i_t would directly be added to C_t (C_t = f_t * C_t + i_t rather than C_t = f_t * C_t + i_t * C_tilde_t).
machine-learning neural-network deep-learning lstm recurrent-neural-net
machine-learning neural-network deep-learning lstm recurrent-neural-net
asked Jul 13 '18 at 0:26
Mar DevMar Dev
1061
asked Jul 13 '18 at 0:26
Mar DevMar Dev
1061
asked Jul 13 '18 at 0:26
Mar DevMar Dev
1061
asked Jul 13 '18 at 0:26
Mar DevMar Dev
1061
asked Jul 13 '18 at 0:26
Mar DevMar Dev
1061
1061
bumped to the homepage by Community♦ 52 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♦ 52 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
$begingroup$
Here is my hypothesis : The $i_t$ can add explainability to the model, as the value of the sigmoid function can give an idea as to how important a particular word is to altering the cell state $C$. This is because $i_t$ lies between 0 and 1. Having single $W$ do both filtering as well as a feature transform of $[h_t-1,x_t]$ not only puts more stress on the matrix (has to do two things at once), but also no longer has this explainability factor.
Example: 2 vectors may require the same transformation $W*v$, but unless you allow seperate sigmoid function to give each an importance, their contribution to the cell state will remain same.
answered Jul 16 '18 at 6:08
Sridhar ThiagarajanSridhar Thiagarajan
2816
$endgroup$
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
);
);
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%2f34401%2fwhy-does-a-filter-need-to-be-applied-to-the-output-of-the-input-gate-before-cell%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
$begingroup$
Here is my hypothesis : The $i_t$ can add explainability to the model, as the value of the sigmoid function can give an idea as to how important a particular word is to altering the cell state $C$. This is because $i_t$ lies between 0 and 1. Having single $W$ do both filtering as well as a feature transform of $[h_t-1,x_t]$ not only puts more stress on the matrix (has to do two things at once), but also no longer has this explainability factor.
Example: 2 vectors may require the same transformation $W*v$, but unless you allow seperate sigmoid function to give each an importance, their contribution to the cell state will remain same.
answered Jul 16 '18 at 6:08
Sridhar ThiagarajanSridhar Thiagarajan
2816
$endgroup$
add a comment |
$begingroup$
Here is my hypothesis : The $i_t$ can add explainability to the model, as the value of the sigmoid function can give an idea as to how important a particular word is to altering the cell state $C$. This is because $i_t$ lies between 0 and 1. Having single $W$ do both filtering as well as a feature transform of $[h_t-1,x_t]$ not only puts more stress on the matrix (has to do two things at once), but also no longer has this explainability factor.
Example: 2 vectors may require the same transformation $W*v$, but unless you allow seperate sigmoid function to give each an importance, their contribution to the cell state will remain same.
answered Jul 16 '18 at 6:08
Sridhar ThiagarajanSridhar Thiagarajan
2816
$endgroup$
add a comment |
$begingroup$
Here is my hypothesis : The $i_t$ can add explainability to the model, as the value of the sigmoid function can give an idea as to how important a particular word is to altering the cell state $C$. This is because $i_t$ lies between 0 and 1. Having single $W$ do both filtering as well as a feature transform of $[h_t-1,x_t]$ not only puts more stress on the matrix (has to do two things at once), but also no longer has this explainability factor.
Example: 2 vectors may require the same transformation $W*v$, but unless you allow seperate sigmoid function to give each an importance, their contribution to the cell state will remain same.
answered Jul 16 '18 at 6:08
Sridhar ThiagarajanSridhar Thiagarajan
2816
$endgroup$
Here is my hypothesis : The $i_t$ can add explainability to the model, as the value of the sigmoid function can give an idea as to how important a particular word is to altering the cell state $C$. This is because $i_t$ lies between 0 and 1. Having single $W$ do both filtering as well as a feature transform of $[h_t-1,x_t]$ not only puts more stress on the matrix (has to do two things at once), but also no longer has this explainability factor.
Example: 2 vectors may require the same transformation $W*v$, but unless you allow seperate sigmoid function to give each an importance, their contribution to the cell state will remain same.
answered Jul 16 '18 at 6:08
Sridhar ThiagarajanSridhar Thiagarajan
2816
answered Jul 16 '18 at 6:08
Sridhar ThiagarajanSridhar Thiagarajan
2816
answered Jul 16 '18 at 6:08
Sridhar ThiagarajanSridhar Thiagarajan
2816
answered Jul 16 '18 at 6:08
Sridhar ThiagarajanSridhar Thiagarajan
2816
2816
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%2f34401%2fwhy-does-a-filter-need-to-be-applied-to-the-output-of-the-input-gate-before-cell%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
