I'm reading the book Hands-On Meta Learning with Python, and in Prototypical networks said:

So, we use episodic training—for each episode, we randomly sample a few data points from each class in our dataset and we call that a support set and train the network using only the support set, instead of the whole dataset.

I think, but I'm not sure, I have understood what "episodic training" is, but what is the meaning of "episodic" or "episode" here?

I'm sorry, I'm not English and I can't guess what it is meaning searching in a dictionary. I know what an episode is, but I don't know what an episode, in this context of training, means.


1 Answer 1


It consists of organizing training in a series of learning problems, each relying on small "support" and "query" sets to mimic the few-shot circumstances encountered during evaluation.(an episode is a single task)


You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .