Thanks to you and the Keras community for those examples. This is one of the highest quality I saw and I love the fact this is executable (and trainable) directly!
New code example on http://keras.io : classification of timeseries with a 1D convnet, created by Hassan Ismail Fawaz. Uses the FordA dataset of timeseries of engine noise measurements.https://keras.io/examples/timeseries/timeseries_classification_from_scratch/ …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Isn’t Conv1D not a good fit for timeseries forecasting because in a timeseries, order matters (the recent past is more important than the distant past). Convolution is for translation-invariant problems ?
-
This is correct, but here we're doing classification, not forecasting. Convolution is a good fit for timeseries classification, in part thanks to translation invariance (it can pick up characteristic patterns independently of their temporal position).
- Show replies
New conversation -
-
-
Great work
@hassanfawaz93 !Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thank you
@fchollet for your code review, it really improved the quality of this tutorial. Finishing my PhD with a contribution example to keras is just perfect. Very much appreciated and I hope the community can build upon this. -
Inception time :)
End of conversation
New conversation -
-
-
Classification of time series....this is new term for me...learnt classification tasks and time series tasks ..this is hybrid.. Thanks for sharing
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This is a great tutorial. Just a question, what if the lengths of the time-series data are various and the length could be a key factor for the classification? Is CNN still good at handling it?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.