What is the default mini-batch size in the fitrnet function

Hi,

I have recently been using the fitrnet function from the Statistics and Machine learning toolbox in order to do regression. Although having used it for a while, I am not sure of the mini-batch size that is used when computing the gradient for training.

I have looked through the documentation for the fitrnet function but have not been able to find the answer. It does speak of iterations, but not the number of iterations per epoch.

Does anyone know where to get this information and if the function uses full-batchs, mini-batches or stochastic GD.

Thanks

Answer 1

[Rahul]

Looking into "fitrnet.m" and verbose data there seems to be no explicit use of “mini batch size” and function is applied on entire “xdata” input variable, so the default mini batch size can be taken as 1.

But in custom training loops with "minibatchqueue" or "training options" the default “mini batch size” is 128.You can refer the following link for more information:

https://www.mathworks.com/help/deeplearning/ref/minibatchqueue.html

This is mostly used in custom training loops or while training deep learning architectures.