Validation of the prediction model with observed (new ) dataset

1 次查看（过去 30 天）
Athira t
Athira t 2020-7-1
编辑： Shubham Rawat 2020-7-24
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);

请先登录，再回答此问题。

回答（1 个）

Shubham Rawat
Shubham Rawat 2020-7-24
编辑：Shubham Rawat 2020-7-24
Hi Athira,
You can use ‘validation data’ options with LSTM networks. But this option is available from R2018b.

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 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