In a neural network, I want to use full batch gradient descent instead of SGD. Currently, I am using code like this (you can see that I forced BatchSize
to be the number of data points):-
trained = NetTrain[net, associationInputToOutput, Method -> {"SGD", "LearningRate"->0.1}, BatchSize -> Length@trainingData]
However, I don't like the code, as it seems misleading to the others since there is the word SGD
inside the code. Is there any other way to force the NetTrain
to use full batch gradient descent?
Many thanks!!