-
|
In the Milestone Project 3: BitPredict we made model 5 which was RNN (LSTM). |
Beta Was this translation helpful? Give feedback.
Answered by
mrdbourke
Oct 11, 2021
Replies: 1 comment
-
|
Hey hey, GRU and LSTM have been found many times to be similar in performance - https://arxiv.org/pdf/1412.3555v1.pdf But in machine learning, often there's a few different ways you could do things. So even though we use an LSTM, it doesn't mean you have to use an LSTM, there could be better models out there. |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
mrdbourke
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hey hey,
GRU and LSTM have been found many times to be similar in performance - https://arxiv.org/pdf/1412.3555v1.pdf
But in machine learning, often there's a few different ways you could do things.
So even though we use an LSTM, it doesn't mean you have to use an LSTM, there could be better models out there.