I have seen time steps, units, batches, samples, sequences, features and more terms seemingly as if they are self-explanatory and yet all describing only in total 3 input dimensions to LSTMs.

If I have X_train[features,timesteps] and y_train[timesteps] (or X(t)=(x1(t),...,xm(t)) and a target y(t)), how do take this input and translate it to 3d input for LSTMs?

Additionally if I have a few X_train[features,timesteps] and y_train[timesteps] all covering same time period but different locations can this be translated to an LSTM problem?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.