I am very new to neural networks and machine learning and I have been making a Bitcoin price predictor to learn it. I was wondering about the number of hidden layers I'd need in a recurrent neural net using LSTM cells.

I have 60 inputs for 30 previous days' close prices in 12-hour intervals and require 1 output for the future 12 hours.

I am doing this with Keras in python 3.6. Any help would be awesome!


1 Answer 1


Number of layers is a hyperparameter. It should be optimized based on train-test split. You can also start with the number of layers from a popular network. Look at kaggle.com and see how many layers do they use in competitions.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.