What is the difference between these two situations? are they the same ?
#1 : train a model 20 epochs on the whole dataset
#2 : divide dataset into n-parts then train the model 20 epochs on each part
20 is a random number just for clarification. do we get the same result (accuracy) between these two situations? and why ?
Side note: this question was raised in my mind when I faced a problem: dataset is bigger than the storage space. So I want to divide it into 4 parts and train the model on each part. But does this effect on accuracy ? does this method of training is correct ?