You can define your deep neural network and use the following trainNetwork syntax: net = trainNetwork(sequences,Y,layers,options). Refer to the expalanation of sequences & Y and arrange the data format accordingly. Also the following code may give you an idea:
inputSize = [13 11 1 5];
nTrainSamples = 50;
filterSize = 5;
numFilters = 20;
numHiddenUnits = 200;
numResponses = 5;
layers = [ ...
sequenceInputLayer(inputSize,'Name','input')
flattenLayer('Name','flatten')
lstmLayer(numHiddenUnits,'Name','lstm','OutputMode','sequence')
fullyConnectedLayer(numResponses, 'Name','fc')
regressionLayer('Name','regression')];
lgraph = layerGraph(layers);
analyzeNetwork(layers)
%%
trainData = arrayfun(@(x)rand([inputSize(:)' 1]),1:nTrainSamples,'UniformOutput',false)';
trainLabels = arrayfun(@(x)rand(numResponses,1),1:nTrainSamples,'UniformOutput',false)';
size(trainData)
size(trainLabels)
%%
options = trainingOptions('adam', ...
'InitialLearnRate',0.005, ...
'LearnRateSchedule','piecewise',...
'MaxEpochs',300, ...
'MiniBatchSize',1024, ...
'Verbose',1, ...
'Plots','training-progress');
net = trainNetwork(trainData,trainLabels,lgraph,options);
