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