So if LSTMs are purposely forgetting, do you need less training data than a CNN?

agibsonccc · on June 10, 2017

LSTMs don't "forget" more than "remember the things that matter". They don't necessarily need less data. They do have a limit on the "length" of time steps they can handle though. Eg: You can't do thousands in to the future (maybe a few hundred or so)

The long part of "LSTM" means remember good long ranging dependencies.