What solvers can be used for LSTM timeseries forecast.

6 Ansichten (letzte 30 Tage)
James Lu
James Lu am 13 Apr. 2018
Beantwortet: mizuki am 14 Apr. 2018
Hi, I have a problem running the example openExample('nnet/TimeSeriesForecastingUsingDeepLearningExample').
First of all, this example wasn't found. After I copied the code and pasted in the editor and run it, it says that I used a invalid solver. Can anyone help me with this? What solver options can I use?
  1 Kommentar
James Lu
James Lu am 13 Apr. 2018
This is the linke to the documentation page: https://www.mathworks.com/help/nnet/examples/time-series-forecasting-using-deep-learning.html

Melden Sie sich an, um zu kommentieren.

Antworten (1)

mizuki
mizuki am 14 Apr. 2018
In R2017b, you can use only 'sgdm' (Stochastic gradient descent with momentum optimizer). In R2018a, there are two additional optimizer options - 'rmsprop' and 'adam.'
See the "solverName" section under trainingoptions documentation: https://.mathworks.com/help/nnet/ref/trainingoptions.html

Kategorien

Mehr zu Sequence and Numeric Feature Data Workflows finden Sie in Help Center und File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by