Thanks. Any examples for timeseries prediction with conv1d layers ?
New tutorial on http://keras.io : weather data timeseries forecastinghttps://keras.io/examples/timeseries/timeseries_weather_forecasting/ …
-
-
-
Conv1D is 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
End of conversation
New conversation -
-
-
"Since every feature has values with varying ranges, we do normalization to confine feature values to a range of [0, 1] before training a neural network. We do this by subtracting the mean and dividing by the standard deviation of each feature." That doesn't confine values.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Perhaps it would be better to breakdown wind direction into sine and cosine, rather than using it raw in degrees/radians.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Happy to see number Keras code examples increasing. This is gonna be so much help for beginners.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Bought the Chinese translation of your book from Taiwan last week, arrived yesterday, reading:pic.twitter.com/2ewxWx12SM
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.