LSTM Two Input one outpot in Matlab Example

13 次查看（过去 30 天）
Yossi
Yossi 2019-2-13
编辑： Tasarruf Bashir 2021-5-10
In Matlab's LSTM Example of sequence-to-sequence regression, there was one input vector (number of cases) and one output (prediction of the number of cases) in the regression.
How in this example I can added two additional vectors and one output (prediction of the number of cases) so the two additiona features will reduce the RMSE?
Thank you

请先登录，再回答此问题。

回答（1 个）

Marcelo Olmedo
Marcelo Olmedo 2020-5-6
Hello! The key is in the data entry. I leave you an example importing training data of 5 input variables and one output. Then the test is done and finally it is graphed. The example is very basic but it will give you a good idea of ​​the procedure
  2 个评论
Mohamed Nedal
Mohamed Nedal 2020-7-3
Hi @Marcelo,
I tried to add a few lines of code to predict new future values of the target output, here's what I added:
%% Forecast the Future
net = resetState(net);
Yforecast = [];
numTimeStepsTest = numel(XTest) + 500; % to forecast new 500 steps in the future
for i = 1:numTimeStepsTest
[net, Yforecast(:,i)] = predictAndUpdateState(net, XTest(:,i), 'ExecutionEnvironment','cpu');
end
but I got this error:
Conversion to double from cell is not possible.
Error in LSTM_multi_motores (line 82)
[net, Yforecast(:,i)] = predictAndUpdateState(net, XTest(:,i),
'ExecutionEnvironment','cpu');
Can you please tell me how to fix this part?
Tasarruf Bashir
Tasarruf Bashir 2021-5-10
编辑：Tasarruf Bashir 2021-5-10
hi@Marcelo Olmedo, i have tried your program with my dataset, having 6 inputs and one output, the rmse value without normalization is very high. but after the normalization the rmse value was dcreased from 1400 to 824. now i am trying to use the technique used in chickenpox example, but couldn't be able to figure out how to use it with multiple variables? can guide me in this regard? thanks in advance

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Linear Regression 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by