What solvers can be used for LSTM timeseries forecast.

Question

James Lu 2018-4-13

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/394789-what-solvers-can-be-used-for-lstm-timeseries-forecast

回答： mizuki 2018-4-14

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 个评论
显示 -1更早的评论隐藏 -1更早的评论

James Lu 2018-4-13

This is the linke to the documentation page: https://www.mathworks.com/help/nnet/examples/time-series-forecasting-using-deep-learning.html

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

mizuki 2018-4-14

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/394789-what-solvers-can-be-used-for-lstm-timeseries-forecast#answer_315031

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