Validation of the prediction model with observed (new ) dataset

1 visualización (últimos 30 días)
Athira t
Athira t el 1 de Jul. de 2020
Editada: Shubham Rawat el 24 de Jul. de 2020
I have written a code in LSTM for prediction. The code is attached below. The predicted the values are matching with YTest dataset with an R squared value of 0.923. so doubt is that how can I validate this model with a new observed values. thanks in advance.
%%define LSTM architecture
inputSize = 8;
numResponses = 1;
numHiddenUnits = 100;
layers = [sequenceInputLayer(inputSize)
lstmLayer(numHiddenUnits)
fullyConnectedLayer(numResponses)
regressionLayer];
opts = trainingOptions('adam', ...
'MaxEpochs',500, ...
'GradientThreshold',1, ...
'InitialLearnRate',0.005, ...
'LearnRateSchedule','piecewise', ...
'LearnRateDropPeriod',125, ...
'LearnRateDropFactor',0.2, ...
'Verbose',0, ...
'Plots','training-progress');
net= trainNetwork(XTrain,YTrain,layers,opts);
%%predict
Ypred1= predict(net,XTest);

Respuestas (1)

Shubham Rawat
Shubham Rawat el 24 de Jul. de 2020
Editada: Shubham Rawat el 24 de Jul. de 2020
Hi Athira,
You can use ‘validation data’ options with LSTM networks. But this option is available from R2018b.

Etiquetas

Community Treasure Hunt

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

Start Hunting!

Translated by