Do I need to engineer lagged features when creating an LSTM for time series forecasting? Unicorn Meta Zoo #1: Why another podcast? Announcing the arrival of Valued Associate #679: Cesar Manara 2019 Moderator Election Q&A - Questionnaire 2019 Community Moderator Election ResultsTime series forecasting with RNN(stateful LSTM) produces constant valuesTime Resolution Changes in Time Series ForecastingLSTM for time series forecasting with H20.aiKeras LSTM with 1D time seriesMultivariate Time-Series forecasting using LSTMMultivariate time series forecasting with LSTMIs there an R tutorial of using LSTM for multivariate time series forecasting?Train LSTM model with multiple time seriesLSTM Time series prediction for multiple multivariate seriesLSTM forecasting on multivariate time series
First instead of 1 when referencing
How do I check if a string is entirely made of the same substring?
Is there really no use for MD5 anymore?
Was Dennis Ritchie being too modest in this quote about C and Pascal?
Is there metaphorical meaning of "aus der Haft entlassen"?
What was Apollo 13's "Little Jolt" after MECO?
How does the mezzoloth's teleportation work?
What makes accurate emulation of old systems a difficult task?
Can I criticise the more senior developers around me for not writing clean code?
Multiple options vs single option UI
"My boss was furious with me and I have been fired" vs. "My boss was furious with me and I was fired"
A faster way to compute the largest prime factor
Mistake in years of experience in resume?
Israeli soda type drink
How to avoid introduction cliches
std::unique_ptr of base class holding reference of derived class does not show warning in gcc compiler while naked pointer shows it. Why?
Drawing a german abacus as in the books of Adam Ries
How can I practically buy stocks?
What *exactly* is electrical current, voltage, and resistance?
How can I close the quickfix window and go back to the file I was editing
How to find the stem of any word?
What is the term for a person whose job is to place products on shelves in stores?
How do I prove this combinatorial identity
What is the best way to deal with NPC-NPC combat?
Do I need to engineer lagged features when creating an LSTM for time series forecasting?
Unicorn Meta Zoo #1: Why another podcast?
Announcing the arrival of Valued Associate #679: Cesar Manara
2019 Moderator Election Q&A - Questionnaire
2019 Community Moderator Election ResultsTime series forecasting with RNN(stateful LSTM) produces constant valuesTime Resolution Changes in Time Series ForecastingLSTM for time series forecasting with H20.aiKeras LSTM with 1D time seriesMultivariate Time-Series forecasting using LSTMMultivariate time series forecasting with LSTMIs there an R tutorial of using LSTM for multivariate time series forecasting?Train LSTM model with multiple time seriesLSTM Time series prediction for multiple multivariate seriesLSTM forecasting on multivariate time series
$begingroup$
Long short-term memory networks are fairly complicated and I haven't completely wrapped my head around them.
It seems to me like the big gain in LSTMs for time series forecasting is the lacking necessity for lagged features: it determines on its own which lagged information is actually significant and remembers it for the next tiestep(s).
Should one still create lagged features as inputs for timesteps when training an LSTM? Like the output of the last timestep, or means and medians of the foregoing timesteps, means and medians for a specific class, distances, differences, etc.?
neural-network time-series lstm rnn feature-engineering
asked Apr 5 at 21:29
DennyDenny
113
$endgroup$
add a comment |
$begingroup$
Long short-term memory networks are fairly complicated and I haven't completely wrapped my head around them.
It seems to me like the big gain in LSTMs for time series forecasting is the lacking necessity for lagged features: it determines on its own which lagged information is actually significant and remembers it for the next tiestep(s).
Should one still create lagged features as inputs for timesteps when training an LSTM? Like the output of the last timestep, or means and medians of the foregoing timesteps, means and medians for a specific class, distances, differences, etc.?
neural-network time-series lstm rnn feature-engineering
asked Apr 5 at 21:29
DennyDenny
113
$endgroup$
add a comment |
$begingroup$
Long short-term memory networks are fairly complicated and I haven't completely wrapped my head around them.
It seems to me like the big gain in LSTMs for time series forecasting is the lacking necessity for lagged features: it determines on its own which lagged information is actually significant and remembers it for the next tiestep(s).
Should one still create lagged features as inputs for timesteps when training an LSTM? Like the output of the last timestep, or means and medians of the foregoing timesteps, means and medians for a specific class, distances, differences, etc.?
neural-network time-series lstm rnn feature-engineering
asked Apr 5 at 21:29
DennyDenny
113
$endgroup$
Long short-term memory networks are fairly complicated and I haven't completely wrapped my head around them.
It seems to me like the big gain in LSTMs for time series forecasting is the lacking necessity for lagged features: it determines on its own which lagged information is actually significant and remembers it for the next tiestep(s).
Should one still create lagged features as inputs for timesteps when training an LSTM? Like the output of the last timestep, or means and medians of the foregoing timesteps, means and medians for a specific class, distances, differences, etc.?
neural-network time-series lstm rnn feature-engineering
neural-network time-series lstm rnn feature-engineering
asked Apr 5 at 21:29
DennyDenny
113
asked Apr 5 at 21:29
DennyDenny
113
asked Apr 5 at 21:29
DennyDenny
113
asked Apr 5 at 21:29
DennyDenny
113
asked Apr 5 at 21:29
DennyDenny
113
113
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
TL;DR
No, you don't have to include lagged variables when using an LSTM.
Long Answer
In an LSTM architecture, your neurons have not only an input gate and an output gate, but they also have a forget gate which causes them to remember values over multiple time intervals. So, you don't have to include any lagged variables in your feature set, since you can expect the LSTM to discover relevant time-depended relationships on its own.
This is not only the case for LSTM's but also for other RNN-architectures.
answered Apr 6 at 9:28
georg_ungeorg_un
318111
$endgroup$
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%2f48717%2fdo-i-need-to-engineer-lagged-features-when-creating-an-lstm-for-time-series-fore%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
$begingroup$
TL;DR
No, you don't have to include lagged variables when using an LSTM.
Long Answer
In an LSTM architecture, your neurons have not only an input gate and an output gate, but they also have a forget gate which causes them to remember values over multiple time intervals. So, you don't have to include any lagged variables in your feature set, since you can expect the LSTM to discover relevant time-depended relationships on its own.
This is not only the case for LSTM's but also for other RNN-architectures.
answered Apr 6 at 9:28
georg_ungeorg_un
318111
$endgroup$
add a comment |
$begingroup$
TL;DR
No, you don't have to include lagged variables when using an LSTM.
Long Answer
In an LSTM architecture, your neurons have not only an input gate and an output gate, but they also have a forget gate which causes them to remember values over multiple time intervals. So, you don't have to include any lagged variables in your feature set, since you can expect the LSTM to discover relevant time-depended relationships on its own.
This is not only the case for LSTM's but also for other RNN-architectures.
answered Apr 6 at 9:28
georg_ungeorg_un
318111
$endgroup$
add a comment |
$begingroup$
TL;DR
No, you don't have to include lagged variables when using an LSTM.
Long Answer
In an LSTM architecture, your neurons have not only an input gate and an output gate, but they also have a forget gate which causes them to remember values over multiple time intervals. So, you don't have to include any lagged variables in your feature set, since you can expect the LSTM to discover relevant time-depended relationships on its own.
This is not only the case for LSTM's but also for other RNN-architectures.
answered Apr 6 at 9:28
georg_ungeorg_un
318111
$endgroup$
TL;DR
No, you don't have to include lagged variables when using an LSTM.
Long Answer
In an LSTM architecture, your neurons have not only an input gate and an output gate, but they also have a forget gate which causes them to remember values over multiple time intervals. So, you don't have to include any lagged variables in your feature set, since you can expect the LSTM to discover relevant time-depended relationships on its own.
This is not only the case for LSTM's but also for other RNN-architectures.
answered Apr 6 at 9:28
georg_ungeorg_un
318111
edited Apr 6 at 9:38
answered Apr 6 at 9:28
georg_ungeorg_un
318111
answered Apr 6 at 9:28
georg_ungeorg_un
318111
answered Apr 6 at 9:28
georg_ungeorg_un
318111
318111
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%2f48717%2fdo-i-need-to-engineer-lagged-features-when-creating-an-lstm-for-time-series-fore%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
