RNNs can only process numeric data, whereas FFNNs can handle any type of data

Question $31$

$1$ pts

What problem do gated recurrent units $($GRUs$)$ and long short$-$term memory $($LSTM$)$ units solve in RNNs$?$

The computational complexity of training large networks

The vanishing gradient problem, enabling the network to learn long$-$term dependencies

The overfitting problem common to all neural networks

The inability of RNNs to process image data