Can CNN train separately instead of learning everything at one time?

Dear friends,

Like our human brain, we can first learn (train) the handwriting 0 and 1. After the traing (and test) accuray is good enough, we only need to study (traing) the hardwriting 2, Instead of cleaning all of learned memory, and relearn handwirting data 0,1, and 2 at the same time.

So, my question is, can CNN do the same thing? Can CNN learn something new, but keep the previous memory ? If yes, the efficiency could be high. Right now, I have to give all of data at the same time, the efficieny is very very low. Please advise me.

Answer 1

[Greg Heath]

I try to have the order of inputs as random and uncorrelated as possible. Otherwise the probability of extensive learning/unlearning is too high..

Thank you for formally accepting my answer

Greg