Which of the following are true or false? 

a. A RNN is designed specifically for processing word sequences. 

b. A RNN is designed to process any time-series data. 

c. An RNN has a limit on how far into the past it can remember. 

d. An n-gram model has a limit on how far into the past it can remember. 

e. An RNN can look into the future. 

f. An RNN must use LSTM units in order to copy information from one time step to the next.