News for hackers. Stuff that matters.

A comment on Exploring LSTMs. Parent comment

Re:Exploring LSTMs by griffinkelly on Saturday June 10, 2017 @11:53AM (#14527770)
So if LSTMs are purposely forgetting, do you need less training data than a CNN?
[ Parent | on HN ]
Re:Exploring LSTMs by agibsonccc on Saturday June 10, 2017 @05:47PM (#14529364)
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.

[ Parent | on HN ]